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:2506.07309v3 Announce Type: replace Abstract: Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation costs? In this work, we address both challenges simultaneously. We introduce ConfQA, a fine-tuning strategy that reduces hallucination rates from 20-40% to below 5% across multiple factuality benchmarks. The approach is simple: when the model answers correctly, it is trained to output the answer; otherwise, it is trained to respond with "I am unsure". Two design choices make this training effective: (1) a dampening prompt ("answer only if you are confident") that explicitly discourages overconfident hallucinations, and (2) training data drawn from atomic factual statements (e.g., knowledge graph attribute values), which calibrates model confidence and yields robust generalization across domains and question types. Building on ConfQA, we
arXiv:2503.24377v2 Announce Type: replace Abstract: Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutio
arXiv:2408.06737v2 Announce Type: replace Abstract: This work presents an extensive study of transformer-based NLP models application for detection of social media posts that contain verifiable factual claims and harmful claims. The study covers various activities, including dataset collection, dataset pre-processing, architecture selection, setup of settings, model training (fine-tuning), model testing, and implementation. The study includes a comprehensive analysis of different models, with a special focus on multilingual models where the same model is capable of processing social media posts in both English and in low-resource languages such as Arabic, Bulgarian, Dutch, Polish, Czech, Slovak. The results obtained from the study were validated against state-of-the-art models, and the comparison demonstrated the robustness of the proposed models. The novelty of this work lies in the development of multi-label multilingual classification models that can simultaneously detect harmful po
arXiv:2609.05401v1 Announce Type: cross Abstract: Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property. Paraphrasing the instruction alone can substantially change predicted progress scores, and can even flip identical robot behavior between failure and success. To measure this failure mode, we introduce ROBORMBENCH, a benchmark with 2,390 real-robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites. Across proprietary and open-source VLMs, paraphrase-induced instability is widespread and severe, grows under more divergent rewrites, and is not reliably reduced by scale or explicit reasoning. Dedicated reward models trained with trajectory-grounded supervision are s
arXiv:2609.05395v1 Announce Type: cross Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing benchmark measures the gap. We introduce the Korean Open Public API Benchmark (KOPA-Bench), comprising 145 real-world tasks. To close this gap, we present EDGE, an Execution-grounded Dynamic Graph for tool-calling data synthEsis driven by live execution. EDGE builds a graph of how each tool's output can feed another's input, keeps only the links that succeed when actually called against the live APIs, and traverses these verified links to synthesize executable multi-step trajectories. Fine-tuned via GRPO on the resulting dataset, our 9B model nearly matches the untuned 27B model from the same family, improving substantially not only on KOPA-Bench but also on the BFCL b
arXiv:2609.05339v1 Announce Type: cross Abstract: Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only $+0.0004 \pm 0.0020$ following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by $+9.91$ or $-13.
arXiv:2609.05333v1 Announce Type: cross Abstract: A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate that word's occurrences by context in its later layers. Testing this belief cleanly requires a construct that holds the word form fixed while its context and intended sense vary in a controlled, labeled way. This manual documents an open toolkit built around such a construct, which we call a bridge form: a single written word that recurs, unchanged, across two or more subject domains with a different sense in each. We describe, and justify, every stage of the pipeline: the declarative specification of bridge forms and their source domains, corpus acquisition from Wikipedia, occurrence localization, layer-wise representation extraction, a domain-pairwise silhouette measurement of separation in the model's representation space, and a paired visualization protocol. Each design choice is pres
arXiv:2609.05314v1 Announce Type: cross Abstract: Building automation systems generate rich sensor data yet remain insight-poor because heterogeneous point naming, missing metadata, and fragmented documentation obstruct their operational use. This systematic review analyses and codes 66 peer-reviewed studies on large language models (LLMs) for HVAC operations published between 2023 and March 2026. Each study is classified across five application families and three LLM method families and assessed for evidence realism, deployment readiness, and the responsibility boundary between the LLM and physical HVAC decisions. The corpus is concentrated in building energy modelling (BEM, 32 of 66 papers), while load forecasting remains too sparse for subfield-level conclusions. Only four studies reach pilot-level evidence, and none reports sustained operational deployment. No study was classified as ready-now for industry adoption; three were near-term and 63 research-only. Nevertheless, several b
arXiv:2609.05175v1 Announce Type: cross Abstract: Measuring the novelty of scientific papers is a central concern in research evaluation and scientometrics. From a recombination perspective, prior studies have largely focused on the co-occurrence of knowledge units to assess the novelty of scientific papers. However, these studies often overlook other relationships between knowledge units. This narrow view may result in inaccurate or incomplete evaluations of novelty for scientific papers. To fill this gap, this study introduces a comprehensive novelty measurement that incorporates three types of relationships between knowledge units: network, semantic, and hierarchical. These relationships are used to quantify the latent distances among knowledge units. Using a dataset of 142,036 articles published in PLoS ONE and a validation dataset from the H1 Connect platform, our results demonstrate that (1) each relationship type captures distinct latent distances between MeSH terms; (2) compare
arXiv:2609.05151v1 Announce Type: cross Abstract: Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large language models (LLMs). Time-to-first-spike (TTFS) coding generates at most one spike per neuron within a time window, yielding extremely low firing rates. However, conventional TTFS SNNs are restricted to specific structures, making it challenging to encode certain blocks in LLM -- such as layer normalization and matrix multiplication --using TTFS. To overcome this limitation, we introduce a reference-based strategy specifically to encode the four core LLM components: embedding layers, layer normalization, attention-related operations and dropout. We construct a fully TTFS-based SNN architecture and train it end-to-end. Experiments on modern LLMs like BERT and GPT-2 demonstrate that our approach achieves performance comparable to ANN counterparts on natural language understanding and common-sens
arXiv:2609.05079v1 Announce Type: cross Abstract: Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses and write research reports, but executing a prescribed analysis is not the same as making a discovery. Existing benchmarks are configured for reproduction: tasks, data, and rubrics are built around a hidden target study, and recovery of its result is rewarded. We present TruthInsightBench, a benchmark configured for discovery. Its 40 blind tasks, drawn from 40 peer-reviewed studies across 10 scientific domains, expose only a neutral scientific objective and frozen data; source conclusions, expected values, and analysis paths are withheld, leaving the agent to determine what claim the data support. A fixed LLM-based judge scores the evidentiary maturity of an agent's own claims along six dimensions, operationalized as 29 artifact-grounded items, with automated, deterministic aggregation and no per-instance human grading, so evaluation can be
arXiv:2609.05059v1 Announce Type: cross Abstract: Whether repeated identical buying questions exhaust a language model's brand recommendations depends on retrieval. Across 300 question-engine cells (50 questions, six engines, 15 runs each, open extraction over 1,470 adjudicated organizations), the five engines answering without web search were still adding never-seen brands at run 15 in 86-92% of cells, with median repertoires of 15-31 organizations; the one retrieval-enabled engine closed its list (median 8 organizations, 64% of cells still adding), matching four earlier deep cells where web-search runs saturated by run ten. Cited-domain accumulation keeps rising at every horizon tested: four deep cells were still adding domains at run 24 with 59-84% of the Chao2 lower-bound estimate observed, and 44% of the retrieval engine's breadth cells were still adding domains at run 15. A single run shows 62-77% of the five-run brand set, and across engines the median question draws 38 organiza
arXiv:2609.04971v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks, often exceeding GPU capacity for long reasoning traces. Existing KV cache compression methods rely on recent queries to estimate future token importance, implicitly assuming these serve as reliable proxies for future attention patterns. We demonstrate that this assumption fails in long-horizon reasoning: certain decoding steps generate Thought Revisiting Tokens (TRT) that re-attend to distant previous context, such as task-solving plans formulated early in the trace. Through systematic analysis, we discover that queries corresponding to the TRT cluster into a small number of similarity groups in the embedding space. Based on this insight, we propose BeaconKV, a training-free KV cache compression method that main
arXiv:2609.04962v1 Announce Type: cross Abstract: What is the relation between understanding and compression, and why does human understanding take such a heavily compressed form? Across information theory, machine learning, and AI research, a substantial tradition identifies understanding with compression-a thought captured in Gregory Chaitin's dictum that "comprehension is compression." Philosophers, by contrast, have characterized understanding in terms of grasping connections, giving explanations, and handling novelty. This paper bridges the two pictures through three interlocking theses. The first concerns the concept of understanding: it serves as an efficient proxy for a distinctive form of robust competence, enabling us to identify whom to trust and whom to learn from. The second concerns the state of understanding: to understand a domain is to possess a mental model of its relational structure that enables prediction, and what enables prediction enables compression, because wh
arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student for downstream RL. At each state, the student matches a next-token distribution supplied by the teacher. As the rollout enters states the teacher would not visit, the teacher-student distribution gap can accumulate. In tool use, this gap becomes consequential because student-written calls execute before supervision and their observations shape later prefixes. Proposer-verifier generation addresses this drift by letting the teacher decide which student-proposed text is retained during generation. Existing formulations govern text but leave tool execution outside their scope. We propose Persistent Teacher Anchoring (PTA), a student-induced but teacher-committed rollout construction. PTA retains chunk-level verification and adds turn-level commitment, allowing a call to reach the environment
arXiv:2609.04689v1 Announce Type: cross Abstract: Early identification of Alzheimer's disease (AD) remains challenging because established assessment methods can be costly, resource-intensive, or unsuitable for population-scale screening. Optical coherence tomography angiography (OCTA) provides non-invasive visualization of retinal microvasculature, but existing approaches often require diagnostic labels and provide limited measurement-level interpretation. We present an explainable OCTA pipeline that integrates annotation-aware vessel segmentation, layer-specific vascular biomarker extraction, label-free phenotyping, and measurement-grounded LLM reporting. Using 117 ROSE-1 images from 39 subjects, we apply annotation-matched segmentation models to superficial vascular complex (SVC), deep vascular complex (DVC), and combined SVC+DVC representations. The models achieve ROC-AUC values of 0.916-0.970 and Dice scores of 0.695-0.781. Six density and fractal-dimension biomarkers form subject
arXiv:2609.04645v1 Announce Type: cross Abstract: Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet a fundamental challenge persists when applying them to recommendation: as representations propagate through multi-step reasoning, both visual and textual signals progressively attenuate - a phenomenon we term cross-modal dilution. To address this, we propose LARK (Latent-Aligned Reasoning frameworK), a two-stage latent reasoning framework with complementary alignment mechanisms within a single VLM. In the first stage, learnable latent tokens are interleaved with multi-step chain-of-thought (CoT) reasoning and explicitly aligned with a frozen vision encoder, serving as visual checkpoints that preserve perceptual details throughout the reasoning chain. In the second stage, the latent representations are projected via a bridge MLP and trained with item-to-item contrastive learning; to prevent the reasoning semantics from fad
arXiv:2609.04585v1 Announce Type: cross Abstract: The Multi-Level Intermediate Representation (MLIR) has made reusable compiler infrastructure practical for domain-specific computation. However, MLIR's strong compile-time type requirements and low-level (C++) extension model can be a poor match for high-level, dynamically specialized languages such as Julia. MLIR has several drawbacks for dynamic programming languages in terms of the type system and level of abstraction. It is thus extremely challenging for non-compiler or scientific computing users to introduce new programming abstractions and express algorithm implementations in a form that remains both natural and optimizable. As a result, library interfaces for linear algebra, mesh processing, partial differential equations, and related domains often sit outside the compiler optimization path. We present JLIR (Julia-native Level Intermediate Representation), a Julia-native intermediate representation framework that brings the main
arXiv:2609.04579v1 Announce Type: cross Abstract: Grounded language-model pipelines can be divided into three stages: selecting an object, retrieving passages for it, and using that evidence to answer. If the selected object must reach the reader, losing it breaks the handoff. Benchmark recall checks the dataset-linked object, which can differ. We audit 600 HybridQA questions across three selector families. On 1,463 resolvable records where the selected object matches the dataset-traced passage, exact key lookup and exact title matching return the object every time. With every ranked rule given the same decoded selected title, body-only BM25 omits it on 389 records (26.6%) at cutoff five, while hybrid retrieval with reranking omits it on 14 (1.0%). The two identities differ on 329 of 1,792 resolvable records. With original-question rankings, their top-five checks disagree on 106 records (5.9%). Frozen reader comparisons associate the aligned object's presence with 28.6 to 31.0 points h
arXiv:2609.04565v1 Announce Type: cross Abstract: Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of tokens, implicitly assuming that effective learning must be token-intensive. We revisit this assumption in the on-policy distillation (OPD) setting, which naturally admits dense teacher supervision at every generated token. Using the Qwen3 family, we discover a counter-intuitive phenomenon: reasoning can be effectively incentivized by an extremely small fraction of generated tokens--as few as one or two tokens per reasoning trajectory, corresponding to only 0.05% of all tokens. Surprisingly, this sparse supervision in most cases matches or surpasses full-token training in improving reasoning ability, despite excluding the vast majority of generated tokens from the training objective. This phenomenon is consistently observed across nine teacher--student config
arXiv:2609.04495v1 Announce Type: cross Abstract: We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this formulation, we introduce an agentic attacker with a dedicated search harness that performs environment reconnaissance, structured reasoning over attack strategies, and adaptive evaluation using victim-agent feedback. Across heterogeneous tasks, we find that increasing attacker test-time compute improves vulnerability discovery and exploitation, while ablations show that explicit strategy management is important for avoiding redundant search and sustaining gains at larger budgets. These results suggest that agentic security evaluations should characterize both the attacker's search procedure and compute budget, rather than treating attack success as a budget-independent property of the victim. More broadly, our findings identify the attacker's adaptive search
arXiv:2609.04486v1 Announce Type: cross Abstract: Intent-based networking realization starts by translating high-level intents into low-level network configurations. Recent approaches have shifted toward LLM-based translation. Despite promising results, most studies focus on translation accuracy and overlook risks associated with deploying the resulting configurations. In this work, we investigate the pre-deployment translation risk of LLM-generated configurations by analyzing the model's uncertainty. We propose to use two uncertainty signals, namely sampling-based predictive uncertainty for translation-risk ranking and token-level entropy for ambiguity-source localization. We evaluate these signals on an ambiguity-controlled test set across different context types and sampling budgets, using a Llama-3.1-8B-Instruct model fine-tuned for intent translation on a vendor-specific switch platform (Juniper EX3300). The results demonstrate that predictive uncertainty provides a useful signal
arXiv:2609.04453v1 Announce Type: cross Abstract: Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, assuming router probabilities provide a reliable importance signal. We observe that this assumption breaks down under over-dispersed routing, a regime associated with aggressive load-balancing during training, in which tokens are distributed nearly uniformly across experts and importance signals collapse. In this regime, perplexity does not predict downstream task accuracy: on gpt-oss-20B, the lowest-perplexity pruning configuration yields the worst mathematical reasoning, while the highest-perplexity configuration preserves it. This does not occur under standard routing (e.g., Mixtral-8x7B-Instruct), where perplexity and accuracy degrade together. Pruning under over-dispersed routing also exposes a capability trade-off in which no single scoring metric dominates: activation-aware scoring pre
arXiv:2609.04445v1 Announce Type: cross Abstract: A conformal certificate can be valid when an LLM answers alone and invalid when the same LLM sees peers that unanimously assert a wrong answer. The question is unchanged; the model's score for the correct answer changes. We call this a score-mechanism shift: clean calibration certifies how the model scores answers alone, but not how it scores them under peer pressure. We show that this shift silently breaks conformal prediction in multi-agent LLM systems. Across open-weight models and multiple-choice QA tasks, coverage falls from a calibrated 90% to 74% under unanimous-wrong peers at the standard alpha = 0.10 operating point. The average hides a sharper failure: by targeting the low-confidence items the certificate still covers, an attacker nearly halves coverage on that subgroup, from 87% to 47%, while the monitored average remains much higher. The failure also reaches the decision layer: a system that should escalate when uncertain ca
arXiv:2609.04362v1 Announce Type: cross Abstract: Music audio-language models are evaluated almost entirely by accuracy on multiple-choice questions. This protocol forces the model to commit to an option, so a lucky guess looks the same as real musical understanding. What is missing is a way to tell when the model does not know the answer, so that it can abstain instead of guessing. The usual solution, an ensemble of independently trained models, is far too expensive here, which leaves the entropy of a single predictive distribution as the only available confidence signal. We instead build pseudo-ensembles from one pretrained model by perturbing its input in ways that cannot change the correct answer, then averaging the resulting distributions over the options. Our main construction simply shuffles the order in which the candidate answers are presented; we also study ensembles built from corrupted audio and from swapped option labels. A pseudo-ensemble gives several predictive distribu
arXiv:2609.04344v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret language model activations, but SAE training and latent labelling are typically repeated for every model. Here, we show that a single shared SAE can replace a collection of dedicated per-model SAEs. Our method, SharedSAE, combines a shared dictionary with model-specific encoder-decoder pairs. Unlike the closest prior method, which discards activation magnitudes and requires all models at inference, SharedSAE instead normalizes only selection scores, preserving magnitudes, and uses model dropout for single-model inference. We train SharedSAE on four 1B-scale base language models spanning distinct families and tokenizers. Despite sharing its latents across models, SharedSAE retains 96.6% of dedicated SAEs' mean explained variance; its latent activations exhibit cross-model correlations 1.8 times as high as separate SAEs aligned post-hoc, and its latent descriptions transfer across mo
arXiv:2609.04343v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior. Unfortunately, these explanations can be unfaithful, failing to reflect the actual reasoning underlying the model's decisions. We consider a setting in which an LLM provides both an answer and an explanation in response to a question. We identify two distinct dimensions of unfaithful explanations: incompleteness, meaning that the explanation omits factors that influence the answer, and unsoundness, meaning that the explanation cites factors that did not influence the model's answer. Existing approaches to improving LLM faithfulness include training-time methods, which require access to model weights and extensive computational resources, and test-time methods that largely focus on addressing unsoundness. We introduce a test-time approach that directly targets incompleteness. We remove f
arXiv:2609.04303v1 Announce Type: cross Abstract: Information abstraction, which groups strategically similar private states into a tractable number of buckets, is essential for scaling game-solving algorithms to large imperfect-information games. Constructing effective abstractions, however, has traditionally required domain-specific evaluators such as hand-strength calculators or equity estimators, which demand expert knowledge and engineering effort and are unavailable for most less-studied games. We propose the Abstraction Agent, a zero-shot pipeline that uses a large language model (LLM) to discover continuous strategic features from a natural-language game description, score private states on these features, and cluster them into abstraction buckets, without any game-specific evaluator, training data, or game-tree traversal during abstraction construction. The pipeline runs in four phases: feature discovery with calibration anchors, batched private-state scoring, correlation-base
arXiv:2609.04298v1 Announce Type: cross Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loo
arXiv:2609.04280v1 Announce Type: cross Abstract: Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness continually evolves as new capabilities are added. We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents). Unlike existing continual-learning benchmarks for agents, which typically place non-stationarity (i.e., what changes over time) in the task stream while keeping the harness fixed, EVOHARNESSBENCH places non-stationarity in the externally supplied harness itself. It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks, comprising 802 tasks, 520 tools, 42 skills, and 62 agents. We evaluate two complementary settings corresponding to the central challenges of harness evolution: deployment evaluation, which isolates retention
arXiv:2609.04272v1 Announce Type: cross Abstract: This study examines the ability of large language models (LLMs) to predict the risk of weather-related forced outages in the distribution grid in a zero-shot framework, without labeled training data. The problem is formulated as a binary severity classification task across three forecast horizons (3h, 6h, 12h), using six years of outage records and high-resolution weather data for a utility service area in central Texas. Four zero-shot LLMs are benchmarked against two supervised classifiers across two input configurations: one using current weather observations and the other using weather forecast data. Results show that supervised models outperform LLMs on macro-F1 and precision, while newer LLM generations achieve competitive scores. Beyond accuracy, LLMs offer complementary strengths in actionable reasoning and geographic scalability, suggesting that combining them with supervised models may be the best practice.
arXiv:2609.04270v1 Announce Type: cross Abstract: Multi-agent LLM pipelines increasingly assign roles, including execution and verification, to models of different capability tiers. This is done because running a flagship model at every stage is expensive. Previous literature has established that verification stages are not always beneficial, but holds reviewer capability roughly fixed relative to the executor. We vary it. We replace the reviewer with models spanning a capability range down to one that cannot solve the problems at all, and measure the outcome of every individual rejection. This is done across a constant set of 100 olympiad mathematics problems. A cross-family mid-tier reviewer improves final accuracy by 12 percentage points, from 52 to 64 percent (p = 0.0005), with zero damaged answers. Same-model self-review attains the highest error-detection rate of any condition (0.85 recall) yet yields no significant gain: it rejects 2.1 times as often for a third the repair rate
arXiv:2609.04263v1 Announce Type: cross Abstract: Low-bit key--value (KV) caches reduce the memory required for autoregressive decoding, but the resulting quality loss depends on the model and quantizer. We keep the quantizer fixed and distill the floating-cache model's behavior into low-rank Q/K/V projection updates while the student executes a physically packed incremental cache. Across three seeds, 4-bit affine-cache adapters recover $54.24\%\pm2.47\%$ of the held-out perplexity gap on TinyLlama-1.1B and $75.96\%\pm4.04\%$ on Gemma-4-12B. On the same frozen NF4 Llama-3.1-8B base, one validation-selected run per quantizer recovers $60.42\%$ under KIVI K2V2 and $37.61\%$ under KVarN K4V2, while preserving 180-case associative retrieval. Gemma's score on an official 4K/8K RULER subset rises from 42.80 with the unadapted 4-bit cache to 48.33 after adaptation (46.15 floating), with substantial task heterogeneity. Finally, a 2-bit rank--token sweep reduces TinyLlama's 2-bit PPL from 576.1
arXiv:2609.04232v1 Announce Type: cross Abstract: This paper offers a unique perspective on how speech technologies are being adopted by community-led heritage language preservation and revitalisation initiatives. As a community-led language maintenance strategy, oral histories play a crucial role in Cantonese language revitalisation in New Zealand. The development of Automatic Speech Recognition (ASR) toolkits, such as Whisper, have expedited what has often been a resource and time-intensive process of transcribing oral history collections. However, there is limited research into the effectiveness of ASR toolkits when applied to code-switched language contexts. Based on Word Error Rate (WER), the best performing Whisper model configuration achieved a WER of 12.10 at the expense of accurately transcribing unsupported non-English segments. However, Whisper remains a useful tool by providing a first-pass transcription using only 1% of the estimated time otherwise needed for manual transc
arXiv:2609.04222v1 Announce Type: cross Abstract: We present GEPARD (Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue), a streaming text-to-speech model for real-time spoken dialogue. GEPARD generates speech autoregressively with an LLM backbone - text and audio embeddings are trained together in a single decoder-only model - and decodes it to a waveform with an FSQ-based neural codec, streaming audio chunk-by-chunk as text arrives. Our central goal is a TTS architecture served by a standard LLM engine (vLLM) without modifying its compute kernels. This defines the overarching design principle: the backbone is a standard full-attention transformer, while all non-trivial auxiliary mechanisms - zero-shot voice cloning, text augmentation, and classifier-free guidance - are moved out of the autoregressive decode loop into prefill, or distilled directly into the weights. On streaming end-to-end inference, a single stream reaches a Real-Time Factor of about
arXiv:2609.05405v1 Announce Type: new Abstract: Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing benchmarks rarely evaluate whether AI systems can reason over a real user's longitudinal wearable record. We introduce WearableQA, a benchmark comprising 4,084 10-option multiple-choice questions constructed from the wearable time series, blood biomarkers, and demographics of 200 real users, each with up to 500 days of daily measurements. WearableQA preserves authentic wearable distributions that include device noise and inter-individual variability. To evaluate distinct reasoning capabilities, we introduce 16 question types organized along two complementary axes: data versus health reasoning, which distinguishes computation over longitudinal measurements from physiological interpretation; and single- versus cross-signal reasoning, which separates reasoning about individual signals from the integration of multiple signals
arXiv:2609.05296v1 Announce Type: new Abstract: Does a simplified legal clause still say what the original said? The checks in current use cannot establish that it does: requiring an identical pair to score highest and an unrelated pair lowest moves lexical overlap and legal force together, so any monotone function of token overlap satisfies both. Our remedy is a dissociation, an item holding surface form fixed while legal force moves. We release LexFlip, 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving 0.93 of the tokens, with a harness scoring metrics, regressors and prompted judges alike. The seven embedding and BERTScore metrics we test spend only 0.022 to 0.039 of their identical-to-unrelated range on such an edit, against 0.670 for bidirectional NLI, the one family the identical-pair check would disqualify. On FrJudge, against a measured human ceiling of r=0.597, a bare length feature outscores every semantic metric and has the lowest
arXiv:2609.05262v1 Announce Type: new Abstract: Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments required for character-based methods and the substantial computational cost of inference on large datasets. This paper introduces a fully self-supervised contrastive learning framework that learns lexical representations directly from raw IPA-transcribed wordlists, without requiring cognacy annotations, alignments, or additional expert input. The model employs a dual contrastive objective: a word-level loss that organizes phonetically similar forms into a coherent space, and an auxiliary language-level loss that encourages the lexical space to reflect broader phonological properties of languages. From the resulting word representations, pairwise language distances are derived and used to infer a global phylogenetic tree of 3,
arXiv:2609.05221v1 Announce Type: new Abstract: Large language models (LLMs) show strong reasoning ability, but their explanations can remain inconsistent, weakly grounded, or difficult to verify. We propose a verifier-guided explainable reasoning framework for transparent educational question answering that combines gold-anchored QLoRA, task-aware symbolic routing, and group-relative RLVR. Qwen2.5-3B-Instruct is first adapted with field-weighted QLoRA supervision anchored to authoritative answers. A lightweight router then assigns logic problems to a FOL/Z3 verifier and physics problems to a formula- and unit aware symbolic solver. Verifier feedback is further used to support candidate evaluation, self-revision, and reward construction during RLVR. Candidate responses are evaluated along three complementary dimensions: P1 for answer correctness, P2 for evidence or unit consistency, and P3 for reasoning depth and explainability. At inference, gold-free self-consistency aggregates multi
arXiv:2609.05189v1 Announce Type: new Abstract: Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapolating to hypothetical scenarios, while field pilot programs are highly costly. In this paper, we propose using large language models (LLMs) as policy-assessment tools adapted from general-purpose models. We present FlexPension-LLM, the first domain-specialized large language model for a hierarchical pension-enrollment prediction task among flexible workers in China, and introduce DKI-RDistill, which injects policy-grounded cues into the prompt, including Probit-derived marginal effects and hukou-province pension rules. The method then uses LoRA/SFT to distill rationale-augmented supervision into an open-weight MoE student, with teacher errors corrected by regenerating those cases under ground-truth labels. On a CHFS 2019 blind split, FlexPension-LLM achieves 0.9316 Composite F1, surpassing
arXiv:2609.05152v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their performance relative to the original model. To address this limitation, we propose DEX-Comp, a two-stage training recipe: Pure Distillation warm-starts the compression model on the uncompressed RAG's correct responses only, and Hard Exploration then runs reinforcement learning solely on queries the uncompressed RAG fails, forcing the model to explore computation patterns better suited to compressed representations. On five open-domain QA benchmarks at retrieval depths from top-5 to top-30, DEX-Comp compresses retrieved contexts by $16\times$ and acce
arXiv:2609.05149v1 Announce Type: new Abstract: Vision-Language Models are commonly evaluated through their final predictions, but understanding whether these decisions are grounded in visual evidence requires tracing how visual information contributes to language-based decisions. With this purpose in mind, we investigate cross-modal information flow in a video-based generative multiple-choice-like setting by applying a layer-wise causal intervention on video-text attention pathways. We target spatial, causal, and temporal visual reasoning. Our results show that visual information is mainly integrated while the model processes the candidate answer options, which serve as the primary textual grounding sites for the final decision. We further show that nouns play an important role as semantic anchors during multimodal enrichment, while verbs are more relevant when temporal relations are processed. Finally, we identify a distinct pattern in temporal reasoning, suggesting that VLMs struggl
arXiv:2609.05143v1 Announce Type: new Abstract: The integration of artificial intelligence (AI), particularly large language models (LLMs), into educational assessment has opened new opportunities to enhance the efficiency and scalability of grading processes. This study presents the design and validation of an AI-assisted scoring framework for written responses in a large-scale national assessment. The proposed approach focuses on short written texts of approximately 150-200 words and incorporates a human-in-the-loop strategy to preserve assessment quality while reducing manual workload. The study is grounded in a real operational context, using data from two recent editions of a nationwide test, each comprising approximately 5,000 student responses. We analyze the alignment between AI-generated scores and human raters across multiple rubric dimensions, as well as the impact of the proposed decision flow on pass/fail outcomes. Results show moderate to high agreement between the model
arXiv:2609.05139v1 Announce Type: new Abstract: Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed across chapters, relations evolve over narrative time, and correct answers may depend jointly on temporal, spatial, and relational constraints. We propose NS-ST-GraphRAG, a neuro-symbolic spatio-temporal GraphRAG framework that integrates ontology-guided extraction, deterministic constraint checking, dual temporal coordinates, spatial scene attributes, and dynamic sub-graph retrieval. Instead of retrieving from a single corpus-level graph, the framework selects the graph state valid for the temporal and spatial scope of a query and grounds generated answers in traceable evidence. We further introduce Red-Chamber-QA, to our knowledge the first open multi-hop question-answering benchmark for classical Chinese literature, with time-, space-, and general-question categories, per-part evidence s
arXiv:2609.05099v1 Announce Type: new Abstract: Automatic identification of code-switched (CS) utterances remains a challenge for language identification (LID) systems, causing such texts to be underrepresented in the training data of Large Language Models. In this paper, we revisit MaskLID, a state-of-the art approach for CS identification, which requires no training and detects arbitrary language combinations. We make three main contributions: (a) we reveal, and address, a major issue of MaskLID: its overreliance on word-level language association scores; (b) we reformulate the underlying optimization algorithm as an Integer Linear Program, enabling us to experiment with a large set of clear and interpretable constraints; (c) each of these improvements vastly improves the baseline system, as we illustrate in experiments involving 10~diverse languages, where we observe a strong boost in performance on CS benchmarks. We release our code and data for reproducibility.
arXiv:2609.05074v1 Announce Type: new Abstract: We propose an influence score to quantify the contribution of attention heads to classification decisions in Transformer-based models designed for prompt injection detection. The score combines directional influence on the logits with structural contribution within the residual stream, enabling a multi-scale analysis at the head, layer, and network levels. Applied to a DeBERTa model specialized for prompt injection detection, our framework reveals distinct decision behaviours between correct and erroneous predictions. Our method provides an effective compromise between fine-grained circuit analysis and global output-based methods, and offers a systematic way to study decision mechanisms in Transformer classifiers.
arXiv:2609.05069v1 Announce Type: new Abstract: Large language models (LLMs) show potential for medical tasks, but their single-turn question-answer format does not reflect how clinical diagnosis is performed in practice. As a result, they remain limited in complex diagnostic settings. We developed Debate-Mixture-of-Agents (DMoA), a novel multi-agent framework that structures role-based interaction to support iterative diagnostic reasoning. Base models and DMoA were evaluated on 297 rare disease cases and 1,719 challenging cases. Across both datasets, DMoA improved most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points over GPT-4o baseline. Ablation experiments showed that the gains were not simply due to the use of more models or longer outputs, but also reflected the contribution of the structured workflow. Further analyses examined how framework design, base model choice, and token budget affected performance. DMoA performed better with
arXiv:2609.05043v1 Announce Type: new Abstract: Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models trained on such data. We introduce EuroAlpaca, a task-preserving localisation pipeline and near-parallel resource covering 50 European languages and regional varieties, together with European-IFEval, a multilingual benchmark for verifiable instruction following. Depending on the example, our pipeline applies field-wise MT while preserving task-critical content or reconstructs a task-equivalent target-language instance, followed by validation of cross-field coherence and target-language consistency. Across LoRA experiments with four LLMs, training on directly translated data improves ROUGE-L and F-BERT on the Aya Evaluation Suite, but reduces accuracy on European-IFEval by 29.8% relative to the unadapted ba
arXiv:2609.05037v1 Announce Type: new Abstract: As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artificial agents (AAs) such as robots, drones, and disembodied AI systems become increasingly embedded in smart city environments, the question of whether and how moral agency is attributed to them takes on new urgency. This paper presents, to the best of our knowledge, the first empirical study comparing how humans and LLMs evaluate perceived moral agency (PMA) across human and autonomous artificial agents varying in embodiment, situated in plausible smart city scenarios. Using an adaptation of a validated PMA scale, we applied a protocol to 190 human participants as well as various LLMs. Our evaluation reveals higher perceptions of moral agency in h
arXiv:2609.05025v1 Announce Type: new Abstract: Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompted and fine-tuned language models. Detecting hallucinations is difficult due to the opaque reasoning processes of LLMs, which often provide little insight into why a model's output may be inaccurate. In this work, we investigate whether an LLM can use an alternative, low level, symbolic competence such as SQL for unsupervised hallucination detection in some high level task. For this, we make an LLM build an SQL database from reference documents. This SQL database is then used for reasoning over the reference and the sampled response in a hallucination detection pipeline that is grounded in the database, thereby providing a neurosymbolic checkup. On RAGTruth and DiaHalu hallucination detection datasets, we find that our approach improves on direct prediction and competes with state-of-the-art