Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2606.12634v2 Announce Type: replace-cross Abstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, API, and answer tokens. Direct self-distillation can supply a denser signal, but in our experiments it can also destroy tool use by rehearsing teacher behavior without identifying which actions the verifier rewards. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for bounded credit weighting rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only credit reference; and detached teacher/student divergence reshapes GRPO token advantages. The deployed student receives only the clean task prompt. Across AppWorld and tau^3-airline, SGCD reports higher held-out point estimates than GRPO-family comparators: AppWorld TGC improves from 42.9 to 45.6 on t
arXiv:2606.09052v3 Announce Type: replace-cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet existing methods either depend on extensively curated or teacher-generated training data, or, when the generator runs unsupervised, reward it by a difficulty heuristic that need not improve the solver. We introduce INFUSER, an iterative co-training framework with two co-evolving roles: a Generator that drafts questions and reference golden answers from a pool of unstructured, automatically collected documents, and a Solver that improves by training on them. The solver is trained with standard correctness rewards against the generator-provided answers, while the generator is rewarded by an optimizer-aware influence score that measures whether each proposed question would actually improve the solver on the target distribution. Because this continuous, noisy influence score is poorly s
arXiv:2605.24661v2 Announce Type: replace-cross Abstract: LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers. To address this gap, this study proposes a unified multi-dimensional framework for measuring reasoning quality in LLMs from a behavioral perspective, operationalizing six theoretically grounded dimensions: Correctness (CQ), Consistency (CS), Robustness (RS), Logical Coherence (LS), Efficiency (ES), and Stability (SS). Extensive experiments on seven LLMs across 975 items from four benchmarks demonstrate that the framework reveals behaviors invisible to accuracy-only metrics. Notably, logical coherence is orthogonal to correctness (r = -0.172, ns), confirming that correct answers can arise from incoherent reasoning, while Claude-Haiku-4.5 achieves the highest multi-dimensional score (Q_bal = 0.
arXiv:2605.09165v2 Announce Type: replace-cross Abstract: Looped language models repeat a set of transformer layers through depth, reducing memory costs and providing natural early-exit points at loop boundaries. However, looped models do not scale as favorably as standard transformers with unique layers. We compare standard and Mixture-of-Experts (MoE) transformers, with and without looping, and find two main results. First, we find Looped-MoE models scale better than the standard baseline while dense looped models do not. We trace this to routing divergence between loops: in Looped-MoE models, different experts are activated on each pass through the same shared layers, recovering expressivity without additional parameters. Our second finding is that looped models have better compute-quality trade-offs with early exits than standard models. Because each loop ends with the same layers that produce the final output, loop boundaries are superior exit points, as confirmed by earlier outpu
arXiv:2604.21495v2 Announce Type: replace-cross Abstract: Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with supervised fine-tuning (SFT) on specific datasets tend to rely on header-operation shortcuts rather than structural reasoning. We introduce TaNOS, a continual pre-training framework comprising three components: (i) header anonymization to reduce lexical memorization, (ii) operation sketches that provide minimal structural cues, and (iii) self-supervised pretraining that constructs correctness-guaranteed program-question pairs from given tables in a program-first manner. By decoupling domain semantics and numerical operation structure, TaNOS improves the transferability of numerical reasoning. Applied to an 8B instruction-tuned model, TaNOS achieves 80.13% execution accuracy on FinQA with only 10% train data, outperforming SFT baseline (73.97%) with full train data and proprietary models
arXiv:2603.14732v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is essential. We evaluate LLM-as-a-judge marking across three physics assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini Pro 3, and committee aggregations against human markers under blind, solution-provided, false-solution, and anchored conditions. We distinguish absolute accuracy from rank-order agreement, since a marking system can match the distribution of human marks while failing to order responses by quality. Across task types, performance is sharply task-dependent. For blind university exam questions ($n=771$) and secondary and university structured questions ($n=1151$), models show robust rank-order agreement with human markers (Spearman $\rho > 0.6$), with official solutions reducing e
arXiv:2602.15029v3 Announce Type: replace-cross Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe. To explain this neural code, we first show that language statistics exhibit translation symmetry (for example, the frequency with which any two months co-occur in text depends only on the time interval between them). We prove that this symmetry governs these geometric structures in high-dimensional word embedding models, and we analytically derive the manifold geometry of word representations. These predictions empirically match large text embedding models and large language models. Moreover, the representational geometry persists at moderate embedding dimension even when the relevant statistics are perturbed (e.g., by removing all sentences in which two m
arXiv:2602.11354v3 Announce Type: replace-cross Abstract: The literature has witnessed an emerging interest in AI agents for automated assessment of scientific papers. Existing benchmarks focus primarily on the computational aspect of this task, testing agents' ability to reproduce or replicate research outcomes when having access to the code and data. This setting, while foundational, (1) fails to capture the inconsistent availability of new data for replication as opposed to reproduction, and (2) lacks ground-truth diversity by focusing only on reproducible papers, thereby failing to evaluate an agent's ability to identify non-replicable research. Furthermore, most benchmarks only evaluate outcomes rather than the replication process. In response, we introduce ReplicatorBench, an end-to-end benchmark, including human-verified replicable and non-replicable research claims in social and behavioral sciences for evaluating AI agents in research replication across three stages: (1) extrac
arXiv:2601.18778v3 Announce Type: replace-cross Abstract: RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretrained LLM leverage latent knowledge to generate an automated curriculum for problems it cannot solve? We explore this with SOAR: An asymmetric self-play framework that uses meta-RL to surface these pedagogical signals. A teacher model proposes synthetic problems for a student model, and is rewarded with its improvement on a subset of hard problems, thus grounding the curriculum in real student progress rather than intrinsic proxy rewards. Our study on the hardest subsets of math benchmarks (0/128 success) reveals three core findings. First, it is possible to realize bilevel meta-RL that unlocks learning under sparse, binary rewards by sharpening a latent capacity of pretrained models to generate useful problems. Second, grounded rewards outperform intri
arXiv:2601.13932v2 Announce Type: replace-cross Abstract: Reaching consensus on massive discussion networks is critical for reducing noise and achieving optimal collective outcomes. However, the natural tendency of humans to preserve their initial ideas constrains the emergence of global solutions. To address this, Collective Intelligence (CI) platforms facilitate the discovery of globally superior solutions. We introduce a dynamical system based on the standard $O(N)$ model to drive the aggregation of semantically similar ideas. The system consists of users represented as nodes in a $d=2$ lattice with nearest-neighbor interactions, where their ideas are represented by semantic vectors computed with a pretrained embedding model. We analyze the system's equilibrium states as a function of the coupling parameter $\beta$. Our results show that $\beta > 0$ drives the system toward a ferromagnetic-like phase (global consensus), while $\beta < 0$ induces an antiferromagnetic-like state (maxi
arXiv:2510.19600v2 Announce Type: replace-cross Abstract: In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce $\textbf{AutoPage}$, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfe
arXiv:2510.09340v2 Announce Type: replace-cross Abstract: Recent language models exhibit significant logical reasoning abilities, yet the mechanisms supporting deductive inference remain poorly understood. This paper studies small transformer-based language models trained from scratch on multi-step deductive tasks, focusing on the distinction between horizontal reasoning, where intermediate steps are generated autoregressively, and vertical reasoning, where inference unfolds implicitly across layers before the first output token is produced. We analyze two synthetic tasks: logical consequence over chains of symbolic implications and root-to-leaf navigation in binary trees. Mechanistic interpretability reveals that Chain-of-Thought supervision enables models to learn rule-based inference rather than statistical shortcuts. In the horizontal setting, a shallow attention-only model develops interpretable circuits for rule completion, rule chaining, and final decision making, largely implem
arXiv:2606.26493v2 Announce Type: replace Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their potential for parallel and iterative generation. However, existing approaches use a single network for both context representation and iterative denoising, forcing one model to serve both roles and limiting its capacity for either role. We propose TwoTower, a block-wise autoregressive diffusion model that decouples these roles into two towers: a frozen AR context tower that causally processes clean tokens, and a trainable diffusion denoiser tower with bidirectional block attention that refines noisy blocks via cross-attention to the context. Built on Nemotron-3-Nano-30B-A3B, an open-weight 30B hybrid Mamba-Transformer MoE model, and trained on approximately 2.1T tokens, Nemotron-Labs-TwoTower retains 98.7% of the autoregressive baseline's quality while offering 2.42X higher wall-clock generation throughput. We release the code and model weigh
arXiv:2606.23375v2 Announce Type: replace Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated risks have emerged. Notably the Swiss Federal Supreme Court uses small on-premises models for tentative translations and short-passage summarization across the four official languages. However, such usage is challenging in the context of Criminal Law. Since rulings and cases employees work on routinely can contain detailed descriptions of violent and sexual offenses, their legitimate work is compromised by refusals and disclaimers due to the activation of model guardrails (over-alignment). To measure this phenomenon, we introduce TF-RefusalBench, a multilingual benchmark for criminal-law translation and summarization derived from public Swiss Supreme Court rulings. TF-RefusalBench contains 5,200 total prompts across French, German, Italian, and English, cor
arXiv:2606.22723v2 Announce Type: replace Abstract: Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended, discursive tasks that demand deeper reasoning and generation capabilities. While the original BLUEX benchmark addressed the scarcity of Portuguese evaluation datasets through multiple-choice questions from Brazilian university entrance exams, it did not cover the more challenging second-phase examinations, which require free-form written responses. In this work, we introduce BLUEX v2, a benchmark derived from the second-phase entrance exams of Brazil's two leading universities: UNICAMP (Comvest) and USP (Fuvest), spanning exam years 2022--2025. Our dataset comprises 395 questions unfolding into 919 graded subquestions, with 55.7% of questions containing associated images (represented as context-aware captions during inference to enable evaluation across both vision-capable and text-only mo
arXiv:2606.05895v2 Announce Type: replace Abstract: Research metrics increasingly use attention as evidence of societal impact. Yet attention serves as evidence only once interpreted, and its meaning depends on the contexts in which it occurs, not on volume alone. Altmetrics records signals in isolation, retaining a count of the attention an output received, or a sequence of when. We address this gap with attention flows, representations that situate a research output's attention in the social settings in which it occurs, the language expressing it, and the time over which it arrives. To evaluate the flow, we construct a benchmark of analogy queries, each testing whether the relationship between two outputs transfers to a third. The count and sequence baselines fail to recover these relationships, whereas flows learned with dynamic contextualised embeddings recover them. The recovered structure survives partial observation and is intrinsic to the attention itself. These findings suppor
arXiv:2605.28183v3 Announce Type: replace Abstract: We introduce BenGER (Benchmark for German Law), a benchmark and dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The dataset combines 596 exam-style free-text legal case tasks across multiple levels of legal education and 531 short doctrinal reasoning tasks. It includes a controlled validation subset of timed human-written solutions under both unaided and human-AI co-creation conditions. We evaluate 12 contemporary LLM systems - closed flagship, efficiency-oriented, and open-weight - with a rubric-aligned LLM-as-a-Judge cross-validated against a multi-rater human-grading layer (three blind reviews per solution, six judge families benchmarked against the human pool). Closed-flagship systems lead the leaderboard across all three corpora, human-AI co-creation measurably improves on unaided human work, and the LLM judge tracks human grading at Pearson r=0.76 and Cohen's \k{appa}=0.60. System rankings
arXiv:2605.19718v2 Announce Type: replace Abstract: CHILDES is a paramount resource for language acquisition studies -- yet computational tools for analyzing its syntactic structure remain limited. Leveraging the recent release of the UD-English-CHILDES treebank with gold-standard Universal Dependencies (UD) annotations, we train a state-of-the-art dependency parser specifically tailored to CHILDES. The parser more accurately captures syntactic patterns in child-adult interactions, outperforming widely used off-the-shelf English parsers, including SpaCy and Stanza. Alongside the parser, we also release a Part-of-Speech tagger and an utterance-level construction tagger, which together form the open-source Syntactic Parsing Toolkit for Child-Adult InTeractions (CAIT). Through a detailed error analysis and a case study tracking the distribution of syntactic constructions across developmental time in CHILDES, we demonstrate the practical utility of the toolkit for large-scale, reproducible
arXiv:2604.22027v2 Announce Type: replace Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed. We investigate this variation by comparing two very different but commonly-used styles of prompting: instruction-based prompts, which describe the task in natural language, and example-based prompts, which provide in-context few-shot demonstration pairs to illustrate the task. We find that, despite large variation in performance as a function of the prompt, the model engages some common underlying mechanisms across different prompts of a task. Specifically, we identify task-specific attention heads whose outputs literally describe the task -- which we dub lexical task heads -- and show that these heads are shared across prompting styles and trigger subsequent answer production. We fu
arXiv:2604.19047v2 Announce Type: replace Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity. This mismatch undermines evaluation validity: retrievers can be unfairly undervalued even when they retrieve documents that provide sufficient evidence, because redundancy across documents is not accounted for in evaluation. On the other hand, retrievers that perform well on standard benchmarks often generalize poorly to real-world corpora with highly similar and redundant documents. We present RARE (Redundancy-Aware Retrieval Evaluation), a framework for constructing realistic benchmarks by (i) decomposing documents into atomic facts to enable precise redundancy tracking and (ii) enhancing LLM-based data generation with CRRF. RAG be
arXiv:2603.19453v3 Announce Type: replace Abstract: We propose an LLM harness that generates code-based policy functions for multi-agent environments, evaluates them with self-play, and refines them using feedback from previous iterations. Following the recent line of work in feedback engineering (the design of which information signals are shown to the LLM during refinement), we compare sparse feedback (scalar reward only) with dense feedback (reward plus social metrics: efficiency, equality, sustainability, peace). In two Sequential Social Dilemmas (Gathering and Cleanup) and with two frontier LLMs (Claude Sonnet 4.6, Gemini 3.1 Pro), dense feedback improves over or matches sparse feedback on all metrics. We explain this asymmetry via feedback aliasing: when the scalar reward maps distinct failure modes into the same value (e.g., under- vs. over-cleaning), social metrics disambiguate and allow the LLM to diagnose which direction of improvement to take. We conclude that social metrics
arXiv:2602.06625v2 Announce Type: replace Abstract: Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-semantic cues such as position, length, format, and model provenance, and evaluation inconsistency that leads to contradictory judgments across different evaluation modes (e.g., pointwise versus pairwise). To address these issues, we propose FairJudge, an adaptive, debiased, and consistent LLM-as-a-Judge. Unlike prior approaches that treat the judge as a static evaluator, FairJudge models judging behavior itself as a learnable and regularized policy. From a data-centric perspective, we construct a high-information-density judging dataset that explicitly injects supervision signals aligned with evaluation behavior. Building on this dataset, we adopt a curriculum-style SFT-DPO-GRPO training paradigm that progressively aligns rubric adherence, bias mitigation, and
arXiv:2602.01070v5 Announce Type: replace Abstract: Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative trajectory generation and selection. For each problem, the agent runs multiple inference iterations. In each iteration, it optionally produces a high-level plan, selects a set of reasoning tools and a compute strategy together with an exploration parameter, and then generates a candidate reasoning trajectory. A process reward model (PRM) serves as a unified control signal: within each iteration, step-level PRM scores are aggregated to guide pruning and expansion during generation, and across iterations, aggregated trajectory rewards are used to select the final response. Across datasets, our dynamic, PRM-guided approach consistently outperforms direct test-time scaling, yielding large gains on MATH-5
arXiv:2601.04126v3 Announce Type: replace Abstract: GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a system that automatically generates functional web environments at scale for GUI agent training. While LLMs perform well on generating a single webpage, building a realistic and functional website with many interconnected pages faces challenges. We address these challenges through unified specification, task-centric test-driven development, and a combination of website seed with reference design image to ensure diversity. Our system also generates verifiable task evaluators enabling dense reward signals for reinforcement learning. Experiments show that InfiniteWeb surpasses commercial coding agents at realistic website construction, and GUI agents trained on our generated environments achieve signi
arXiv:2512.21002v3 Announce Type: replace Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge distillation (KD) over lengthy sequences with prompt (P), chain-of-thought (CoT), and answer (A) sections makes the process computationally expensive. In this work, we investigate how the allocation of supervision across different sections (P, CoT, A) affects student performance. Our analysis shows that selective KD over only the CoT tokens can be effective when the prompt and answer information is encompassed by it. Building on this insight, we establish a truncation protocol to quantify computation-quality tradeoffs as a function of sequence length. We observe that beyond a specific length, longer training sequences provide marginal returns for downstream performance but require substantially higher memory and FLOPs. To this end, training on only the first $50\
arXiv:2510.17139v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first prompts LLMs to generate answers or pseudo-documents that serve as new queries, relying purely on the model's parametric knowledge or contextual information. The second applies reinforcement learning (RL) to fine-tune LLMs for query rewriting, directly optimizing retrieval metrics. While having respective advantages and limitations, the two approaches have not been compared under consistent experimental conditions. In this work, we present the first systematic comparison of prompting-based and RL-based query augmentation across diverse benchmarks, including evidence-seeking, ad hoc, and tool retrieval. Our key finding is that under a compute-aware comparison setting, simple, training-free query augmentation often performs on par with, or even surpasses, more e
arXiv:2508.01682v3 Announce Type: replace Abstract: Process Reward Models (PRMs), which assign fine-grained scores to intermediate reasoning steps within a solution trajectory, have emerged as a promising approach to enhance the reasoning quality of Large Language Models (LLMs). However, most existing PRMs rely on a unidirectional left-to-right (L2R) evaluation scheme, which restricts their utilization of global context. In light of this challenge, we propose a novel bidirectional evaluation paradigm, named Bidirectional Process Reward Model (BiPRM). BiPRM incorporates a parallel right-to-left (R2L) evaluation stream, implemented via prompt reversal, alongside the conventional L2R flow. Then a gating mechanism is introduced to adaptively fuse the reward scores from both streams to yield a holistic quality assessment. Remarkably, compared to the original PRM, BiPRM introduces only a 0.3% parameter increase for the gating module, and the parallel execution of two streams incurs merely 5%
arXiv:2506.17294v3 Announce Type: replace Abstract: The advent of artificial intelligence has propelled AI-Generated Game Commentary (AI-GGC) into a rapidly expanding research area, offering advantages such as scalable availability and personalized narration. However, existing studies remain fragmented, and a systematic survey that unifies prior efforts is still lacking. To bridge this gap, our survey introduces a unified framework that systematically organizes the AI-GGC landscape. We present a novel taxonomy focused on three core commentator capabilities: Live Observation, Strategic Analysis, and Historical Recall, and further categorize commentary into three corresponding types: Descriptive Commentary, Analytical Commentary, and Background Commentary. Building on this structure, we provide an in-depth review of methods, datasets, and evaluation metrics, analyzing their strengths and limitations. Finally, we highlight key challenges and point out promising directions for future resea
arXiv:2504.07385v3 Announce Type: replace Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness. Meanwhile, using LLMs themselves as evaluators without external grounding remains unreliable for objective tasks, as they systematically over-accept incorrect answers, fabricate supporting rationales, and degrade sharply on questions that fall outside their training data. We propose Search-AuGmented Evaluation (SAGE), a framework to assess LLM outputs without fixed ground-truth answers. Unlike conventional metrics that compare to static references or depend solely on LLM-as-a-judge knowledge, SAGE acts as an agent that actively retrieves and synthesizes external evidence. It iteratively generates web queries, collects information, summarizes findings, and refines subsequent searches through reflection. By reducing dependence
arXiv:2502.15845v2 Announce Type: replace Abstract: Large Language Models (LLMs) often hallucinate, limiting their reliability in sensitive applications. In black-box settings, several self-consistency-based techniques have been proposed for hallucination detection. We empirically show that these methods perform nearly as well as a supervised (black-box) oracle, leaving limited room for further gains within this paradigm. To address this limitation, we explore cross-model consistency checking between the target model and an additional verifier LLM. With this extra information, we observe improved oracle performance compared to purely self-consistency-based methods. We then propose a budget-friendly, two-stage detection algorithm that calls the verifier model only for a subset of cases. It dynamically switches between self-consistency and cross-consistency based on an uncertainty interval of the self-consistency classifier. We provide a geometric interpretation of consistency-based hall
arXiv:2410.12341v4 Announce Type: replace Abstract: As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy. This feedback loop has been shown to induce model collapse, typically characterized by a loss of diversity in generated content. However, existing work offers a limited understanding of this phenomenon and relies on mitigation strategies that assume access to human-authored data. In this paper, we conduct extensive simulations across multiple datasets and LLMs to address key gaps in the study of model collapse. First, we introduce model-intrinsic measures based on next-token probability distributions, showing that model collapse corresponds to an increasing concentration of probability mass on a small set of tokens. Second, we demonstrate that model collapse is also associated with a loss of common sense, as measured by a decline in commonsense inference accuracy. Thir
arXiv:2606.32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision methods aim to solve this problem by scoring intermediate steps, from intrinsic confidence to self-distillation and embedding similarities. However, it is common practice to evaluate them by measuring the downstream performance of a training pipeline that integrates them. This is expensive, conflates supervision quality with training engineering confounders, and renders different methodological families requiring distinct training setups incomparable. As a result, dense supervision methods are rarely benchmarked on common ground. We introduce QVal, a training-free testbed for directly evaluating dense supervision signals. Given a state-action pair, QVal measures
arXiv:2606.32022v1 Announce Type: cross Abstract: Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anchors and unembedding readout disagree on the chosen span, apparent motion may reflect measurement drift rather than computation. We introduce \emph{Semantic Reference Frames} (SemRF), an anchor-based formalism separating semantic measurement from residual dynamics. A SemRF fixes anchors and measures states against them. Pseudo-inverse tying gives exact synchronization; under restricted bi-invertibility, SemRF yields stable semantic-basis coordinates, distortion bounds, and near-identity changes. With the frame fixed, residual computation becomes a depthwise semantic trajectory. The anchors induce a semantic Voronoi diagram: distance, or evidence such as logits, assigns each layer to a coarse cell, while coordinates retain within-cell motion and margins. We def
arXiv:2606.31966v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded environments remains underexplored. To address this gap, we introduce MECoBench, a multimodal embodied cooperation benchmark with an evaluation platform spanning diverse real-world tasks, two cooperation structures, and three collaboration modes. Through extensive experiments across various MLLMs, we summarize three key findings: (i) Collaboration generally improves embodied task completion, but its benefits depend on balancing collaborative gains against coordination complexity. (ii) Communication is essential to collaboration gains, while the best collaboration mode depends on team size and model capability. (iii) Moreover, collaboration improves robustness under noisy priors and exploration conditions. Generally, MECoBench provides a systematic testbed for understanding the mechanisms and lim
arXiv:2606.31963v1 Announce Type: cross Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments. This is only well posed after fixing the model's residual-stream gauge, which we show is architecture-dependent: LayerNorm residual charts have permutation gauge $S_d$ (up to a global sign flip), while RMSNorm charts with generic per-channel gain have signed-permutation gauge $B_d = S_d \ltimes \{\pm 1\}^d$. Permutation-only alignment is therefore symmetry-incomplete for RMSNorm models. We introduce sign-marginalized Hungarian matching and prove a sharp failure mode: with decorrelated coordinates, raw signed-correlation matching has a structural permutation-accuracy ceiling at the positive-sign fraction of the true gauge, which sign-marginalization removes. We then make coordinate-preserving transport, not function-level merging, the primary object: composing saved-
arXiv:2606.31859v1 Announce Type: cross Abstract: Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W[RMSNorm(h_{l-1}), RMSNorm(u_l)]). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two findings. First, a depth-stability result: a convex (Highway-style) form of the gate reintroduces vanishing gradients and fails to train beyond ~20 layers, whereas the additive, identity-preserving form trains stably at all depths we tested. Second, an emergence-with-scale result: trained from scratch across five sizes (60M-1B parameters, multi-see
arXiv:2606.31781v1 Announce Type: cross Abstract: Log parsing is a fundamental step in automated log analysis, transforming raw system logs into structured event templates for downstream tasks such as anomaly detection and system monitoring. Existing log parsing methods range from rule-based and clustering-based approaches to neural models that learn semantic representations from log messages. However, neural approaches typically rely on dense matrix multiplications, which can result in high computational cost and energy consumption. This paper presents SpikeLogBERT, a spiking neural network framework for energy-efficient log parsing. The proposed model integrates a spiking transformer architecture with knowledge distillation from a BERT teacher model, enabling spike-driven computation while preserving semantic representation capability. By leveraging sparse spike activations and event-driven processing, the number of active operations during inference can be significantly reduced. As
arXiv:2606.31779v1 Announce Type: cross Abstract: Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replacing decoded tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth, Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent reasoning. We therefore ask whether looped Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded Transformer that processes K latent blocks in parallel for R iterations, with a cross-entropy loss on each latent position's gold CoT-step token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped Transformers with parallel su
arXiv:2606.31694v1 Announce Type: cross Abstract: For robots manipulating open-world objects, tactile representations must generalize to unseen materials. We introduce RCT (Robotic Contact Tactile), a robot-collected touch-vision-language dataset with 29,279 tactile frames from full robot presses on 122 industrial reference materials in 7 categories, recorded with three DIGIT sensors at multiple contact positions. RCT preserves each press as a contact sequence, enabling held-out evaluation across materials, categories, sensors, contact positions, and contact sequences. Frames from one press are strongly correlated: frame-random splits can place near-duplicate observations of the same physical interaction in both training and test. With the encoder held fixed, removing contact-sequence overlap reduces tactile-to-text Recall@1 by 17.7 percentage points. When materials are additionally held out at training time, performance drops sharply, leaving held-out-material Recall@1 at 25.1 +/- 6.1
arXiv:2606.31693v1 Announce Type: cross Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol
arXiv:2606.31543v1 Announce Type: cross Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making selection among candidates, not just generation, the central challenge. I present a solver for ARC-AGI-2, a few-shot visual reasoning benchmark, built around two principles: (i) treating reasoning modalities as search operators, generating diverse candidates independently across text, image, and code channels, and (ii) context-preserving holistic judging, in which a judge model jointly compares all candidate reasoning traces within a single long-context prompt. Unlike self-consistency or majority voting, this approach reliably recovers correct minority hypotheses on tasks where the modal answer is wrong. On the ARC Prize semi-private evaluation set, the solver achieves 72.9 percent at USD 38.99 per task - the highest score on the verified leaderboard at the time of writing, exceeding th
arXiv:2606.31519v1 Announce Type: cross Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased. To address these limitations, we propose RaBitQCache, a novel sparse attention framework that utilizes randomized rotated binary quantization and high-throughput binary-INT4 arithmetic to efficiently estimate attention weights. Our proxy score serves as an unbiased estimator with a proven error bound, enabling adaptive Top-p retrieval that dynamically adjusts the token budget based on actual attention sparsity. We further implement a hardware-aware system with asynchronous pipelining and lazy updates to mask overhead. Evaluations demonstrate that RaBitQCache significantly accelerates inference and reduces memory I/O while preserving generation quality compared to state-o
arXiv:2606.31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism. From a Popperian view, a generated program is a conjecture and a test-execution violation is an oracle-relative, executable counterexample, so feedback's value should be attributed not to re-exposure to failing code but to whether the conjecture is opened to external, executable criticism. As the third stage of a falsification-centered measurement program, this study builds a placebo-controlled instrument that decomposes the feedback packet against a blind-resampling baseline at matched output-generation budget and against content-free, shape-matched placebos. The contribution is not a new repair algorithm but a reflexive methodology (packet decomposition, placebo mirroring, matched-budget discordant-pair tests, fresh-generation confirm
arXiv:2606.31484v1 Announce Type: cross Abstract: Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without the need for any re-training. However, existing methods follow a think-first-then-decide paradigm, i.e., they first sample multiple reasoning paths, which inevitably leads to overgeneration, then prune or stop unnecessary paths to compensate. In contrast, decide-first-then-think, i.e., first identifying points that are likely to lead to desirable generations, has been underexplored so far. Following this paradigm, we propose Fork-think with confidence, that first identifies forking points using model confidence in a single seeding path, then triggers thinking, sampling multiple continuations and aggregating them for the final response. Our experiments across three models and three reasoning benchmarks show that Fork-think reduces the token consumption by up to 30% and run-time by up to 57%, while performing comparable to or better than pa
arXiv:2606.31435v1 Announce Type: cross Abstract: Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing benchmarks either isolate text editing or entangle it with code and tool execution, it remains unclear whether LLMs can directly and faithfully execute these compositional, order-sensitive data refinement recipes. To fill this gap, we introduce CDR-Bench, a comprehensive benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators. Our benchmark evaluates models across atomic, order-agnostic, and order-sensitive settings, leveraging deterministic reference outputs to enable exact evaluation. Experiments on 10+ state-of-the-art LLMs reveal consistent failure patterns: performance degrades sharply in compositional settings, and order-sensitive recipe success collapses. These findings underline that
arXiv:2606.31407v1 Announce Type: cross Abstract: Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common entropy-based methods, such as Semantic Entropy (SE), rely on output diversity. Yet our analysis shows that overconfident visual embeddings suppress output diversity under stochastic decoding, causing SE to underestimate uncertainty in such cases. Recent methods instead probe output diversity through input perturbations, including textual paraphrasing or joint text-image perturbations, and show improved performance. We study these approaches and reveals that the resulting variability is often dominated by textual changes rather than visual evidence, causing uncertainty estimates to reflect prompt sensitivity rather than visual ambiguity. We therefore propose Visual Semantic Entropy (VSE), which perturbs only the image to probe nearby visual variations while keeping the text query fixed. VSE measures uncertainty by c
arXiv:2606.31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned strategy distribution - a phenomenon termed evaluator preference coupling. Prior work has documented this coupling and established a diagnostic framework (EPC) to measure it, but has not investigated whether calibration techniques can mitigate the effect. We present the first study of evaluator calibration as mitigation: applying probability calibration to the evaluator's pairwise judgments to reduce spurious preference propagation. In a controlled within-subjects experiment (N=5) comparing standard binary TTRL (win/loss) with confidence-calibrated TTRL (probability-weighted updates) using DeepSeek-V4-Pro as executor and GLM5.2 as evaluator, we find that calibration reduces the coupling coefficient gamma by 20-49% and Jensen-Shannon divergence by 45-67%. A symmetric-LR control confirms th
arXiv:2606.31272v1 Announce Type: cross Abstract: AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Governing them needs a stable notion of skill identity, yet cryptographic hashing is engineered to destroy the very similarity we need, as a one-character edit scrambles the digest. We present a compact, locality-sensitive fingerprint that embeds each component of a skill and projects it to bits with a multi-bank SimHash, giving a fixed 120-byte signature compared in constant time by Hamming distance. Our central claim is that keeping the fingerprint as a per-component triple (prompt, code, tools), rather than a single score, is what makes it useful: the triple recovers skill-family identity through paraphrase, renaming, refactoring, and controlled code translation when another component remains shared, while independent multilingual reimplementation is not recov
arXiv:2606.31179v1 Announce Type: cross Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications. We introduce HealthAgentBench, a suite of 54 agentic healthcare tasks across 7 categories each with its unique environment. The benchmark suite spans diverse workflows throughout the patient journey and a broad range of modalities. Each task is designed to replicate an end-to-end clinical workflow: given minimal instructions, an agent must explore raw healthcare data, operate within a complex environment, and execute multi-step solutions that go beyond naive prompting. A final task success rate is reported to provide a single, interpretable metric for HealthAgentBench overall performance for each agent. Evaluating frontier agents on HealthAgentBench, we find that overall task success rate remains low, underscoring the difficulty of the suite. The stro
arXiv:2606.31163v1 Announce Type: cross Abstract: Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundary. Serving all queries through a single large model consumes full GPU capacity regardless of query complexity while offering no mechanism for geographic routing. Mixture-of-Experts architectures do not address this routing occurs between expert layers within the model after data has already arrived at the endpoint, with all experts loaded in memory regardless of query complexity. We propose a classifier-gated routing architecture that enforces compliance by design. A trained encoder classifier sits before any decoder inference, evaluating each query for complexity and data sensitivity, then routing it to an appropriately sized dense model in