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:2503.20182v2 Announce Type: replace Abstract: As large language models (LLMs) increasingly function as human-like assistants exhibiting human-like personality traits, understanding their behavioral characteristics becomes essential for responsible AI development. However, existing evaluation efforts, which often adapt human psychological assessments such as the Big Five Inventory (BFI), face two significant limitations. First, these approaches often lack reliability, as minor prompt variations can lead to inconsistent test results. Second, the theoretical foundations of these tools, rooted in human studies, are misaligned with the computational nature of LLMs, thereby limiting their validity in predicting real-world model behavior. To address these limitations, we introduce the Core Sentiment Inventory (CSI), a novel personality trait evaluation instrument designed from the ground up and specifically tailored to the unique characteristics of LLMs. CSI covers both English and Chin
arXiv:2502.13428v2 Announce Type: replace Abstract: This work investigates how to improve large language model (LLM)-based reasoning for knowledge base question answering (KBQA) via Monte Carlo Tree Search (MCTS). Applying MCTS to LLM-based KBQA remains challenging because reward design is difficult and rollout-based search is computationally expensive. Existing MCTS-style methods either rely on direct LLM scoring or require substantial data to train separate reward models, and they often provide rewards only at terminal states. To address these limitations, we propose Fast MCTS, which replaces terminal rollouts with an information gain (IG) reward for intermediate states. The IG reward is implemented as a question-conditioned PPL-ratio proxy over sanitized interaction histories, computed by forward passes of an open-source instruction LLM without additional reward-model training. Experiments on four KBQA benchmarks show that Fast MCTS consistently outperforms linear baselines and gene
arXiv:2402.09696v3 Announce Type: replace Abstract: Current Grammar Error Correction (GEC) initiatives tend to focus on major languages, with less attention given to low-resource languages like Esperanto. In this article, we begin to bridge this gap by first conducting a comprehensive frequency analysis using the Eo-GP dataset, created explicitly for this purpose. We then introduce the Eo-GEC dataset, derived from authentic user cases and annotated with fine-grained linguistic details for error identification. Leveraging GPT-3.5 and GPT-4, our experiments show that GPT-4 outperforms GPT-3.5 in both automated and human evaluations, highlighting its efficacy in addressing Esperanto's grammatical peculiarities and illustrating the potential of advanced language models to enhance GEC strategies for less commonly studied languages.
arXiv:2205.11930v3 Announce Type: replace Abstract: Human ratings are the gold standard in NLG evaluation. The standard protocol is to collect ratings of generated text, average across annotators, and rank NLG systems by their average scores. However, little consideration has been given as to whether this approach faithfully captures human preferences. Analyzing this standard protocol through the lens of utility theory in economics, we identify the implicit assumptions it makes about annotators. These assumptions are often violated in practice, in which case annotator ratings cease to reflect their preferences. The most egregious violations come from using Likert scales, which provably reverse the direction of the true preference in certain cases. We suggest improvements to the standard protocol to make it more theoretically sound, but even in its improved form, it cannot be used to evaluate open-ended tasks like story generation. For the latter, we propose a new human evaluation proto
arXiv:1908.06361v2 Announce Type: replace Abstract: Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases remain poorly understood. We show that for any embedding model that implicitly does matrix factorization, debiasing vectors post hoc using subspace projection (Bolukbasi et al., 2016) is, under certain conditions, equivalent to training on an unbiased corpus. We also prove that WEAT, the most common association test for word embeddings, systematically overestimates bias. Given that the subspace projection method is provably effective, we use it to derive a new measure of association called the $\textit{relational inner product association}$ (RIPA). Experiments with RIPA reveal that, on average, skipgram with negative sampling (SGNS) does not make most words any more gendered than they are in the training corpus. However, for gender-stereotyped words, SGNS actually amplifie
arXiv:2608.18066v1 Announce Type: cross Abstract: Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a comprehensive re-evaluation of two memory-based methods, broadening the scope of evaluation along two axes: (1) including multiple runs to quantify variance, and (2) randomly shuffling the tasks to investigate the effect of task order. Through these experiments, we make two observations that expose the fragility of current methods: First, agent evaluation is inherently noisy in complex environments and on multi-step tasks, and stacking a self-improving loop on top can further amplify this noise. Second, the agent's improvement is highly dependent on task order. Prior works often adopt default orderings that impose an implicit curriculum, act
arXiv:2608.17987v1 Announce Type: cross Abstract: The rapid growth of social media has greatly influenced political discourse, highlighting the need to understand individual political ideologies and their temporal dynamics. This task faces challenges such as data scarcity, abundant non-political content, costly and bias-prone manual annotation, and difficulty in modeling future ideological inclinations. To address these issues, we propose TSN4PI, a unified framework for tracking the evolution of political ideologies on social media. It includes two core modules. The PIDN uses large language models with style transfer and unsupervised domain adaptation to enable robust ideology detection and filter irrelevant content from noisy, cross-domain data. The PIPN employs temporal graph neural networks to predict future ideological shifts, enabling comprehensive analysis of ideology presence, intensity, and evolution. We release two large-scale datasets for noncommercial research use to facilit
arXiv:2608.17941v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the same exploration budget to samples with different difficulty levels is inefficient: easy samples may receive redundant rollouts, whereas difficult but learnable samples may receive too little exploration. Existing adaptive schedulers address this mismatch through curriculum-based sample selection or non-uniform rollout allocation based on estimated sample difficulty. However, obtaining reliable online difficulty estimates remains challenging: dedicated probing adds substantial generation overhead, whereas history-based estimators face a cold start with no initial observations and stale feedback, and typically ignore relations among samples. To address these limitations, we propose a plug-and-play graph-based online difficulty estimator that shares rollout feedback acro
arXiv:2608.17804v1 Announce Type: cross Abstract: Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, terminal training-rollout audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probe
arXiv:2608.17719v1 Announce Type: cross Abstract: Context: Software systems that depend on commercial large language model APIs must migrate to successor versions when vendors deprecate older models. Migration decisions typically rely on aggregate benchmark scores, which compress heterogeneous item-level behaviour into a single net figure. Objective: We measure what that compression conceals. Method: On three pairwise upgrades in the GPT-5.4 to GPT-5.6 Sol product sequence, we query 900 public benchmark items (graduate-level knowledge, olympiad mathematics, instruction following) 50 times per item per model, classify each item as reliably improved, reliably regressed, practically equivalent, or inconclusive under false-discovery-rate control and a practical-significance threshold, and calibrate the results against a label-permutation null. Results: Across all nine migration-benchmark cells, reliable improvements and reliable regressions coexist. Edges with aggregate gains of up to 7.3
arXiv:2608.17644v1 Announce Type: cross Abstract: Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much the person would be willing to pay for an item. A growing body of work estimates a utility function from these judgments and then chooses actions based on their estimated utility. This pipeline assumes the judgments are approximately self-consistent: that a single utility function can reproduce them. But are they? To study this question, we measure the self-consistency of cardinal LLM preference judgments. For example, the difference in stated willingness-to-pay between two items should match the stated payment that makes a person indifferent to exchanging them. We develop statistical tests and interpretable measures of how far observed responses depart from the best-fitting self-consistent utility function. Experiments with flight, apartment, and hotel examples across six LLMs reveal larg
arXiv:2608.17616v1 Announce Type: cross Abstract: We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples inference cost from context length, achieving $O(N)$ preprocessing and $O(1)$ query cost with peak GPU memory that does not grow with $N$. At 128K tokens, MoNe reduces both compute and peak GPU memory by approximately 80% compared to ICL with only 6.4% parameter overhead. MoNe generalizes to context lengths far beyond the backbone's native window, achieving strong performance on needle-in-a-haystack and word extraction benchmarks from RULER, where ICL degrades sharply.
arXiv:2608.17567v1 Announce Type: cross Abstract: Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for molecular discovery within and beyond their pretraining domain remains unclear. Herein, we systematically benchmark four molecular language models across six virtual molecular libraries spanning drug discovery, organic materials, and catalysis. Native molecular language model embeddings show substantial variation in discovery performance across libraries, whereas molecular fingerprints provide a consistently strong and robust baseline. Consistent with a potential domain-representation mismatch, we show that explicit domain adaptation substantially improves representation performance. Fine-tuning molecular language model encoders on structures from the target virtual library consistently improves sample efficiency, with several adapted encoders emerging as the top-perform
arXiv:2608.17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 sam
arXiv:2608.17550v1 Announce Type: cross Abstract: Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For Multimodal Large Language Models (MLLMs), the core challenge is not only perception, but representation: scientific pages interleave text with Structured Academic Elements (SAEs) such as tables, formulas, charts, and pseudocode, whose structure, data, and logic are poorly preserved by common surrogates like Markdown. We therefore propose Compilable Academic Document Parsing (CADP), a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page. To support this setting, we introduce CADP-Bench, an expert-verified benchmark of full academic pages containing tightly coupled text and mult
arXiv:2608.17445v1 Announce Type: cross Abstract: Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting a harmful task into individually permissible requests and combining their answers. Defending against them therefore requires a stateful monitor that considers requests together. If it can group all requests for one attacker task, it can stop the attack. However, attackers can use unlinkable identities and combine answers elsewhere, leaving no reliable grouping signal. We ask whether decomposition attacks can still be stopped under this setting. For a fixed attack strategy without retries, we prove that the achievable security and utility tradeoff depends entirely on how benign requests for the same capabilities are grouped. Persistent, recognizable groups permit a useful defense; fresh, indistinguishable groups do not. When attackers can retry and learn from
arXiv:2608.17063v1 Announce Type: cross Abstract: Large language models can be fine-tuned into specialized classifiers that perform well across diverse text tasks and make complex judgments, but they typically expose only final labels, leaving the decision knowledge acquired through fine-tuning implicit within the model. We study how to mine this internal decision knowledge from a fine-tuned classifier and encode it in an executable representation that can be inspected, validated, and reused beyond the source classifier. We introduce J-Miner, which mines text-level named concepts by aggregating vocabulary-aligned internal signals across layers and token positions, and uses the classifier's own predictions to learn executable decision rules over them. This process distills local internal readouts into an explicit classifier-level knowledge representation. Across multiple classification tasks, J-Miner rules reproduce up to 98.3\% of source-classifier decisions and achieve 6.0--29.5 perce
arXiv:2608.17053v1 Announce Type: cross Abstract: A bounded agent may obtain information for a decision from its own past, from peers, or from both sources. Retaining task-relevant history can reduce later communication, while a peer message can supply what memory lacks. Under limits on both resources, how should an agent allocate its information budget? Given a fixed task and decision rule, the memory and message rate pairs attaining a performance threshold form an achievable region under specified rules for using history and peer observations. We call its efficient boundary the remembering--signaling frontier. Across conditions where history permits the same maximum reduction in task loss, we hypothesize that a bounded agent will need less peer communication when it obtains a larger loss reduction from history. In preliminary referential games, target repetition coincided with shorter successful messages, while predictability from a hidden cyclic rule did not shorten them. Experiment
arXiv:2608.16934v1 Announce Type: cross Abstract: RTL code generation is a critical stage in hardware design, and the emergence of agentic systems offers new opportunities to automate this process. To generate correct RTL code, agents must understand sequential behavior, including how signals evolve and propagate over multiple clock cycles. However, effectively conveying such temporal information to agents remains a significant challenge. RTL code does not expose cycle-level signal behavior for a specific execution, whereas full simulation waveforms are too voluminous and noisy for effective LLM analysis. To address these limitations, we study how human engineers reason about sequential behavior and identify three requirements for effective feedback: it should be event-addressable, dependency-traceable, and iteratively-queryable. Guided by these requirements, we propose \textit{SeqFeed}, which comprises two complementary mechanisms: (1) \textit{SeQuery}, an SQL-like waveform query lang
arXiv:2608.15382v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty. We propose a reproducible, graph-centered evaluation framework for intervention-oriented LLM behavior in healthcare and stress-test it in a cardiovascular pilot. The framework has four components: (i) a domain causal knowledge graph in which assertions are first-class, provenance-preserving nodes with stable identifiers; (ii) a scenario-conditioned subgraph extraction step that, given any clinical scenario, retrieves the relevant reified-assertion subgraph; (iii) four controlled grounding conditions that vary how the retrieved subgraph is composed into the model's context (ungrounded C1, knowledge-graph C2, causal-graph C3, integrated C4); and (iv) an automated scoring pipeline, anchored on assertion ident
arXiv:2602.14784v1 Announce Type: cross Abstract: Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or retrieval-augmented generation (RAG), effective segmentation determines how well systems can locate and return relevant information. However, traditional methods, such as fixed-length or coherence-based segmentation, ignore user intent, leading to chunks that split answers or contain irrelevant noise. We introduce Intent-Driven Dynamic Chunking (IDC), a novel approach that uses predicted user queries to guide document segmentation. IDC leverages a Large Language Model to generate likely user intents for a document and then employs a dynamic programming algorithm to find the globally optimal chunk boundaries. This represents a novel application of DP to intent-aware segmentation that avoids greedy pitfalls. We evaluated IDC on six diverse question-answering datasets, including news
arXiv:2311.06273v1 Announce Type: cross Abstract: The rise of ChatGPT has brought a notable shift to the AI sector, with its exceptional conversational skills and deep grasp of language. Recognizing its value across different areas, our study investigates ChatGPT's capacity to predict stock market movements using only social media tweets and sentiment analysis. We aim to see if ChatGPT can tap into the vast sentiment data on platforms like Twitter to offer insightful predictions about stock trends. We focus on determining if a tweet has a positive, negative, or neutral effect on two big tech giants Microsoft and Google's stock value. Our findings highlight a positive link between ChatGPT's evaluations and the following days stock results for both tech companies. This research enriches our view on ChatGPT's adaptability and emphasizes the growing importance of AI in shaping financial market forecasts.
arXiv:2608.18072v1 Announce Type: new Abstract: Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology reports from CT examinations of the chest, abdomen, and pelvis dictated by 15 board-certified radiologists in 2023 and 2024. A multi-agent AI pipeline was developed to perform report structuring and quality assurance (QA). The system structured the report into standardized anatomical sections at the sentence level using regex rules and local large language models. It also detected mismatches between the Findings and Impression sections, or within sections; gender-anatomy conflicts; and undocumented communication of critical findings. Two board-certified radiologists independently evaluated a 45-report subset. Results: The multi-agent system structured the Findings sections of all reports (22,270 sentences) into a predefined anatomical format
arXiv:2608.18062v1 Announce Type: new Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attributed to a limited understanding of which tokenizer properties affect which aspects of downstream performance. We introduce TokEval, a framework of tokenizer evaluation metrics that goes beyond standard measures like fertility and compression rate to capture linguistically and structurally meaningful properties, e.g., UTF-8 character boundary integrity and digit place-value boundary alignment for mathematics. To validate whether these metrics are predictive of downstream model performance, we conduct controlled language model pretraining experiments, varying solely the tokenizers' training data mixture, pretokenization strategy, and training algorithm. We evaluate the resulting models on bits-per-byte (a tokenizer-agnostic version of perplexity) and several benchma
arXiv:2608.18041v1 Announce Type: new Abstract: Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention weights refine that count, which sums every writer in the corpus together. This paper claims a second parameter, phase, which signed weights learned from a corpus do not supply. Phase exists only between meanings: it determines how coactivated meanings combine, and it can reverse what a meaning contributes while that meaning stays fully present. A speaker can set phase in the signal through linguistic form; encounters install phase relations and history distributes them. Population averaging deletes history-indexed phase: agent-deindexed corpora identify the population marginal state and determine no individual or dyadic state, at any scale. The standard transformer has no explicit representation for phase in frozen inference, and the interpretability program measuring progress by monosem
arXiv:2608.18027v1 Announce Type: new Abstract: Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference. We instantiate CoE with diverse feedback mechanisms, including model self-feedback and environmental signals such as correctness or public coding test pass rates, and evaluate across math, coding, and knowledge domains using 8 LLMs, including GPT-5, Gemini-2.5 Pro, Claude-4.5 Sonnet. Our study shows that leveraging iterative experience consistently outperforms feedback-free baselines, achieving substantial gains with self feedback alone, alongside a 5.6% overall i
arXiv:2608.18011v1 Announce Type: new Abstract: Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics and code. Linguistic puzzles invert this: the solver must first discover the system before reasoning within it. We present the IOL-AI Challenge, an open-science competition run on the unseen problems of the International Linguistics Olympiad (IOL) 2026 Individual Contest, evaluated both automatically and, for the first time, by members of the official IOL Jury under the same rubrics applied to human contestants. The challenge drew 731 submissions from 46 teams under a strict compute budget (one T4, 30 mins). We additionally benchmark 15 unconstrained frontier and open models, with Claude Opus 4.8 earning a jury score equivalent to a gold medal, while both resource-constrained systems we submitted for jury grading scored in the range of the bottom 5% of contestants. Capability was not determined by scale: 14B submissions outperform models tw
arXiv:2608.17994v1 Announce Type: new Abstract: Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference answer exists. However, objective tasks introduce a distinct reliability challenge for reference-free LLM judging. In the absence of a reference answer, the judge evaluates factual correctness either through its parametric knowledge or through tool augmentation. Although the former enables efficient evaluation, the judge may hallucinate or lack sufficient evidence for its verdict. Conversely, tool augmentation can provide additional evidence but introduces extra computational cost and requires an appropriate mechanism to determine when and how that evidence should be used reliably. More importantly, neither approach alone provides formal control over the risk of accepted verdicts or guarantees their reliability at a specif
arXiv:2608.17979v1 Announce Type: new Abstract: Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this assumption is challenged by distribution shifts caused by changes in genre, time, and AI-assisted writing. Existing AV benchmarks typically study these factors in isolation and focus predominantly on English, limiting our understanding of model robustness under realistic conditions. We introduce AVShift, the first German benchmark for systematically evaluating AV under multiple distribution shifts. AVShift comprises over 150,000 text pairs spanning three genres and 21 years, enabling controlled evaluation of cross-genre, temporal, and AI-era shifts within a unified framework. We benchmark representative feature-based, embedding-based, and LLM-based approaches. Our experiments show that fine-tuned LLMs generalize best across genres and benefit substantially from stylistical
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these distant cognitive leaps remain poorly understood. Traditional attention-based interpretability often fails to capture true semantic proximity due to routing artifacts like attention sinks. In this paper, we bypass attention weights to directly analyze the dynamic geometry of the hidden state manifold, proving that deep LLM latent spaces natively organize into Small-World networks. By sparsifying the continuous similarity matrices of long-context representations into unweighted graphs, we trace the connectivity between highly disjoint semantic anchors across two distinct architectures. Our findings reveal a sharp topological phase transition: while early syntactic layers remain entirely fractured, deep reasoning layers abruptly compress massive conceptual distances into highly navigable pathway
arXiv:2608.17938v1 Announce Type: new Abstract: Small language models can grade open-ended examination answers as reliably as substantially more expensive models when they grade against an explicit rubric. We test this claim as the design principle behind any-to-bench: a frontier model reads source documents once, at ingestion, to extract each question and its rubric; lower-cost models then perform all repeated grading work. We evaluate six cost-efficient model configurations from two model families at three reasoning-effort levels. Each configuration answers 24 open-ended examination questions, and each also grades every answer sheet three times, yielding 3,456 per-question grades. Scores depend overwhelmingly on the answer being graded: answer identity explains 95.6% of score variance, whereas judge identity explains only 0.2%. Raising a writer's reasoning effort moves earned scores by as much as 0.143 of full marks, while raising a judge's reasoning effort moves assigned scores by a
arXiv:2608.17931v1 Announce Type: new Abstract: Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is said. Speech Sentiment Analysis plays a critical role in decoding these paralinguistic cues for diverse real-world applications such as recruitment and customer service. However, existing Speech Sentiment Analysis research faces two primary limitations. First, dominant approaches rely on text-centric pipelines that cascade Automatic Speech Recognition with text analysis. This process inevitably discards essential acoustic features like prosody and tone, failing to capture attitudinal meanings in acoustically ambiguous utterances. Second, current benchmarks suffer from a mismatch in label granularity, prioritizing basic emotions (e.g., happy, sad) over the nuanced interpersonal stances (e.g., confident, impatient) necessary for social sensitivity. To address these limitations, we propose a
arXiv:2608.17911v1 Announce Type: new Abstract: As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded memory interface. We study this evidence-reachability problem in long-term conversational memory, where retrieval still relies heavily on semantic similarity. This works well for topical recall, but it often misses earlier experiences, plans, or motivations that are semantically distant from the later events they help explain. Existing memory graphs provide cross-memory structure, yet links driven mainly by semantic overlap can duplicate what the host retriever already recovers. We argue that link construction should instead prioritize a sparse set of retriever-complementary associations. We present CABLE (Complementary Antecedent-Based Linking and Expansion), a plug-in augmentation that constructs links designed to extend the host retriever's direct semantic reach
arXiv:2608.17895v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional documents remains incompletely evaluated. Existing benchmarks emphasize information extraction, require external domain knowledge, or cover professional documents only as one of many settings. They are also largely English- or Chinese-centric, leaving other languages and Russian, in particular, substantially underrepresented. To address these limitations, we introduce BEAR-Bench (Bilingual Enterprise and Academic Reasoning), a self-contained, complex English-and-Russian benchmark comprising 1000 human-annotated questions based on text-rich business and scientific documents. We evaluate 16 proprietary and open-weight MLLMs, including Gemini 3.1 Pro and Qwen3.5-397B, on BEAR-Bench and observe clear headroom even for the strongest systems. Finally, we use the resulting model outputs to c
arXiv:2608.17866v1 Announce Type: new Abstract: Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity of a given answer, however, consistently yield so-called pseudoprompts, unintelligible strings of tokens which can lack human interpretability. We argue that this is a consequence of the ill-posedness of the prompt optimisation task. By reframing the task as a Bayesian posterior inference over prompts, we propose an efficient algorithm to sample prompts which are both efficient (in terms of perplexity) and human readable. We compare our approach with state of the art alternatives showing on a real data set a marked improvement over a range of metrics.
arXiv:2608.17843v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model behavior remain unclear. We investigate this question through geometric reasoning, using parametric CAD constraints as a controlled testbed for separating local pairwise relations from sketch-level constraint status. By probing the hidden states of six frozen decoder-only LLMs, we examine four properties: linear decodability, forced-choice generation, activation-level influence, and behavioral steerability. Pretraining substantially improves the decoding of local geometric relations, and this advantage persists after accounting for positional cues with shuffled-order controls. In contrast, sketch-level DOF status is already highly decodable from randomly initialized representations and improves only modestly with pretraining, indicating that much of its probe performance is available without le
arXiv:2608.17827v1 Announce Type: new Abstract: Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily reflect English-language and US-centric settings, and often only evaluate task performance. In this paper, we present first results of M\"OVE, a holistic evaluation framework for the German public sector, examining three rarely considered governance dimensions: energy consumption, provider transparency, and knowledge of German-party positions. Our results reveal significant trade-offs, with no single model excelling across all dimensions: estimated energy consumption varies more than 60-fold and is not explained by model size alone, information disclosure varies systematically across providers, and European models do not exhibit stronger knowledge of German party positions. Model selection for public institutions thus cannot rely on performance rankings alone. Instead, evalu
arXiv:2608.17809v1 Announce Type: new Abstract: Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of the weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief; chains of thought that expl
arXiv:2608.17795v1 Announce Type: new Abstract: Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled candidate SQLs and assigning correctness scores to unseen queries, yet they still provide limited visibility into the signals behind each verification. To address this limitation, we propose TraceSQL, a lightweight and traceable verification model built on explicit diagnostic features. TraceSQL combines 67 features capturing question ambiguity, quest
arXiv:2608.17781v1 Announce Type: new Abstract: ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than input-local interactions. We test this in retrieval-augmented generation (RAG), where evidence utility can be measured under controlled interventions. Holding query, evidence, task, scoring, and intervention fixed, nine readers disagree on effect sign in 33\% of jointly affected cells; reader$\times$query interaction explains 29.8\% of utility variance versus an 8.4\% permutation null; and self-selected evidence improves F1 by $+0.031$ ($t=3.39$). We then ask the sharper question: \emph{which components of this heterogeneity are stable reader properties across queries?} Separating three measurable objects---evidence \emph{activity}, \emph{ordinal preference}, and \emph{conditional signed direction}---we find ordinal reader geometry stable across four independent settings (split
arXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the score by 7.7 points, more than every data and recipe effect we measured. That null is our first result. The real changes live where accuracy cannot see. Base models never think in Greek: 0 of 1,000 reasoning traces, even when the question is Greek, so the model answers correctly while reasoning in a form its user cannot read, audit, or correct. After supervised fine-tuning (SFT), every released checkpoint reasons in the language of the question on ~98% of items, one family at 3x fewer tokens, with judged grammaticality improving on all four models and general ability within a few points of each base: nothing was forgotten, and fluency was gained.
arXiv:2608.17605v1 Announce Type: new Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews multi-turn conversational AI across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around datasets and benchmarks, modeling paradigms, training strategies, evaluation setups, and cross-cutting challenges. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a sessi
arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following procedural guidance and improving it from execution evidence are distinct capabilities. Inference time loops can repair skills but do not improve the model that writes the next one. We study how to organize execution experience from intermediate skills into training states for an optimizer. We introduce WER (Write, Execute, and Refine), a multi-phase framework that trains a Skill Optimizer outside a frozen executor. The optimizer proposes skills, a frozen agent executes each repeatedly, and a programmatic verifier scores the outcomes. The scores provide relative credit and select mixed-outcome records. Matched successful and failed trajectories from these records form the next phase's refinement states, so the optimizer learns from the consequences of its earlier ou
arXiv:2608.17583v1 Announce Type: new Abstract: Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderation judgments vary across languages. We audit TikTok in France, Italy, and Sweden with sockpuppet accounts representing four age personas (13, 16, 19, 40), collecting 36,971 videos from passive For-You-page scrolling and active sessions that scroll, search for harm keywords, and scroll again. To scale annotation, we validate four multimodal LLMs against native-speaker labels on a 300-video reference set. Gemini 2.5 Flash with eight sampled frames plus text performs best (aggregate kappa = 0.42), at half the per-call cost of native-video upload, and we apply it to a 10% sample for approximately \$50 in total API spend across both modalities. Keyword search returns 35-56% harmful content, a 1.5-7.5x increase over the scrolling baseline in ten of twelve country-age combinations; the spike is
arXiv:2608.17536v1 Announce Type: new Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor interpretability for complex ones, making it difficult to meet the requirements for both answer quality and efficiency in high-risk scenarios. To address this issue, this paper proposes CoAL-RAG, a complexity-aware legal retrieval-augmented generation method, which constructs a multi-dimensional evaluation mechanism based on ``question essence'' and ``retrieval consistency'' to enable adaptive routing of retrieval strategies. First, the reasoning demand is quantified according to the logical structure of the question. Then, the discrepancy between semantic retrieval and keyword retrieval is utilized to indirectly reflect problem complexity, thereby selecting the most appropriate retrieval strategy and dynamically filtering contextual information. Experimental results demonstrate that the prop
arXiv:2608.17534v1 Announce Type: new Abstract: Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localiz
arXiv:2608.17516v1 Announce Type: new Abstract: Gender bias or other social biases in large language models (LLMs) are frequently evaluated with question answering or survey benchmarks where the LLM needs to give a response in a predefined answer format. It is well known in survey science that the answer format has a substantial impact on answers, just as LLMs are sensitive to the prompt wording. However, to our knowledge it has not been studied yet how changes in answer format impact the measurement of gender bias in LLMs and their alignment with human response distributions. We evaluate three instruction-tuned models on the BBQ benchmark and OpinionQA survey data across closed-ended, Likert-scaled and open-ended formats, comparing bias measurement and distributional alignment under otherwise identical conditions. We find that answer format does substantially alter measured outcomes, including reversals in order rankings. These differences arise because each format elicits distinct re
arXiv:2608.17454v1 Announce Type: new Abstract: This paper presents a pipeline for analyzing media bias and framing in online news. The pipeline groups articles into topics and events, adds named-entity and sentiment annotations, and compares news sources through people mentions, source-level tone, and event-level coverage patterns. We apply it to 8,358 Albanian news articles collected from GDELT and compare the resulting annotations with GDELT's automated annotations. The results show moderate agreement for sentiment and entity extraction, as well as additional person-entity pairs that can potentially support the bias analysis. We compare two annotation prompts and find that stricter sentiment-validation rules remove label-score inconsistencies but increase execution time and reduce annotation coverage. Based on these results, the simpler prompt is used for the rest of the analysis. We have provided sample analysis on source-level framing pro les, person-level tone differences across
arXiv:2608.17399v1 Announce Type: new Abstract: Text which has been translated from another language tends to carry with it evidence of translation$\unicode{x2014}$hence, it is often referred to as $\textit{translationese}$. Multilingual large language models (MLLMs) generate text in a variety of languages. However, it is still unclear if MLLMs' generations resemble internal translation (from English or, potentially, other languages) and, thus, result in translationese. Here, we ask the following research questions: (1) Does text generated by MLLMs resemble translationese? (2) How does translationese produced by MLLMs differ from translationese produced through direct translation? We leverage established indicators of translated text to evaluate text generated by state-of-the-art MLLMs in five languages, comparing to both non-translated and human-written baselines in order to isolate translationese from other kinds of interference. Through the use of high-accuracy classification models
arXiv:2608.17379v1 Announce Type: new Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at runtime, and speedup over frontier libraries across GEMM and attention workloads on H100 and B200 GPUs. Our evaluation shows that architecture-specific PTX capability remains uneven: success rates fall substantially on complex attention backward workloads, and executing the target instructions does not necessarily translate into competitive performance. No evaluated model consistently matches frontier libraries across the suite. We further adapt Qwen3.6-27B using supervised fine-tuning. Repair-conditioned training improves several tasks, but generalization remains uneven; data coverage, balance, and the quality of the reasoning teacher matter in addition to dataset size. PTXBench provides an auditab