跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 15:29 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 16:12 — 2026-11-09 16:12（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 15:29最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 5,189 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 15:27（北京时间）
新论文 · v1arXiv:2610.39735

From the Transformer to a Formal Semantics of Coordinated Transformations

Marco Giunti, Fabrizia Giulia Garavaglia

原文摘要

We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular mathematical instantiation. Representational vectors receive both extensional reference and ordered intensional interpretations, while parameter structures acquire relative, second-level interpretations that determine how argument properties are preserved, replaced, or combined. This yields the notion of a transforming concept: a parameterized transformation whose numerical action is coordinated with a corresponding property-level map. We then distinguish the common algebraic-semantic core of these systems from their architecture-specific functional organization, allowing different mathematical instantiations and mechanical realizations of the same abstract system type. The framework is applied to attention heads and residual connections, providing semantic explanations that depend only on the shared algebraic-semantic core and their local functional organization and therefore generalize beyond the standard Transformer. These analyses also reveal the modularity of the framework: complex architectures can be decomposed into simpler semantically coordinated subsystems whose organization may recur across different abstract system types.

cs.AI · cs.CL · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39676

Event-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams

Sergei Fedorchenko, Max Zehnder, Nikola Zubić, Rong Zou, Davide Scaramuzza

原文摘要

Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and models. We introduce Event-SAMA-239K, a synthetic-event conversion of the SAMA-239K grounded video-chat corpus and all additional SAMA training data: 30,650 video clips and 392,162 images. Optical-flow, FILM or saccade upsampling followed by a linear event generator preserves all mask, referring-expression and dialogue annotations. We also introduce Event-SAMA, adapting SAMA-4B with a two-channel polarity patch embedding initialised from pretrained RGB weights and a zero-initialised event adapter. End-to-end training yields 24.37 $\mathcal{J}\&\mathcal{F}$ on MeViS valid_u and 22.33 $\mathcal{J}\&\mathcal{F}$ on the converted ReVOS valid subset, establishing the first event-native RVOS baseline (RGB SAMA-4B: 55.4 on MeViS). Frozen RGB SAMA-4B with pseudo-RGB renderings or E2VID reconstructions of the same events scores 13.23 and 15.94 $\mathcal{J}\&\mathcal{F}$. Without retraining, Event-SAMA works on real event-camera recordings when the accumulation window matches their event density. A seed-controlled ablation with a measured noise floor of 0.47 $\mathcal{J}\&\mathcal{F}$ finds gains from diverse training sources over MeViS alone (+4.99), RGB-mean event-stem initialisation (+4.33), and a trainable SAM2 mask decoder (+2.76); the event adapter, partial ViT unfreezing and event polarity are within noise at this budget. An earlier, partially converted corpus snapshot trained with the identical recipe scores 1.38 $\mathcal{J}\&\mathcal{F}$ higher on MeViS and 1.12 higher on ReVOS. Both are single runs that also differ in schedule length, so we draw no conclusion about corpus scale.

cs.LG · cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39671

Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

Lingkai Kong, Yuzhe Gu, Haiteng Zhao, Zijian Wu, Youqing Fang, Zhouqi Hua, Yanan Sun, Kai Chen 等 9 位作者

原文摘要

Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupled knowledge acquisition and reasoning, beyond factual retrieval and aggregation or learning solely from a preassembled context. We study self-learning -- autonomously retrieving, studying, and applying knowledge from long-form reference materials on the fly. To investigate this capability, we formulate a textbook-based mathematical problem-solving task. LLMs must navigate textbook exposition, learn and apply relevant principles, and construct proofs for exercises, with reference solutions withheld. We introduce a BookNavigator interface to support this human-inspired study process and incentivize self-learning through reinforcement learning (RL) with fine-grained rewards. Experiments show that our method improves performance across in-domain and out-of-domain textbooks and subjects, raising Intern-S2-Preview-35B's overall proof accuracy from 51.5% to 79.5% and outperforming RL-trained textbook-free and fixed-retrieval baselines. These gains extend to complex long-context benchmarks involving different task types, with improvements over the base model of 1.7 and 2.3 percentage points on BrowseComp-Plus and CL-bench, respectively. Together, these findings suggest that RL can foster a domain-agnostic self-learning strategy, highlighting the potential of self-learning from long-form corpora to strengthen broader problem-solving capabilities on complex, long-context tasks.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.19491

Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule

Euijin Hong, Guannan Qu

原文摘要

Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a deep network sees during training can be highly anisotropic, with a few directions queried frequently while most are seen rarely. Preconditioning methods address this anisotropy by wrapping extra processing around this buffer and leave the momentum update itself unchanged. We propose Activation-Keyed Momentum (AK-Momentum), which builds direction-awareness into the momentum update rule. The gradient of a linear layer splits into an input activation that acts as a $\textit{key}$ and an output-side error that acts as a $\textit{value}$. Keying on that activation, AK-Momentum updates the momentum buffer by the canonical delta rule, so each direction is forgotten at a rate set by how often it appears. We prove that it is a valid momentum, that it applies the input-side curvature correction without matrix inversion, and that it clears stale directions faster than EMA under both a fixed and a drifting optimum. It is a drop-in replacement for the momentum buffer of any optimizer, its coefficient transfers across widths under $μ$P, and its extra compute stays between $22.2\%$ and $25.0\%$ of a gated-MLP block's linear cost with no persistent memory. In FineWeb-Edu pretraining, AdamW with AK-Momentum (AK-AdamW) reaches AdamW's validation loss in up to $46.64 \pm 4.52\%$ fewer steps at 67M and $22.14 \pm 0.81\%$ at 370M over three seeds, and the gain persists at 1B on a Chinchilla-optimal budget. A Muon baseline tuned under the same protocol sits above AK-AdamW at both language-model scales, and the gain holds for SGD, ResNet-18, and ViT-Tiny on CIFAR-10. Training-time diagnostics confirm the predicted mechanism, better gradient tracking and healthier input directions. Code is available at https://github.com/euijinh/AK-Momentum.

cs.LG · cs.CL · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39602

Evaluating Cultural Knowledge Editing in Vision-Language Models

Malvina Nikandrou, Georgios Pantazopoulos, Ioannis Konstas, Alessandro Suglia

原文摘要

Current Vision-Language Models (VLMs) frequently fail to recognize culture-specific concepts, especially from underrepresented regions. Effectively injecting this long-tail knowledge into existing models remains a challenge. In this work, we investigate knowledge editing as a targeted alternative by introducing CulturalBind, a benchmark comprising 3.2K images of 1K concepts from 6 domains, designed to evaluate culture-aware cross-modal knowledge as well as concept-level knowledge editing in VLMs. Pre-edit evaluation reveals that textual and visual knowledge is decoupled: models often demonstrate text-based knowledge of cultural concepts but fail to identify them from images. We then evaluate editing methods in single and sequential scenarios. Although current methods successfully correct individual visual recognition errors, they exhibit low cross-modal portability, failing to integrate edits into the model's broader parametric knowledge. Furthermore, performance degrades rapidly under sequential editing, highlighting the need for comprehensive adaptation approaches that better consolidate multimodal knowledge over time.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39590

Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin

Paula Chikaodinaka Anyanwu, Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Ifeoluwa Dorcas Awotunde, Danielle Blanche Kapsa, Tassallah Abdullahi, Clemencia Siro, Idris Abdulmumin 等 10 位作者

原文摘要

As large language models (LLMs) become more widespread in Africa, their safety in low-resource languages remains largely untested since most red-teaming work focuses on English. This study evaluates six state-of-the-art LLMs using 400 explicit adversarial prompts in Yoruba and Nigerian Pidgin, categorised into four harm categories. The responses were scored by native-speaker annotators and reliability was assessed using Cohen's $κ$. While models that rejected up to 69% of English prompts rejected as few as 0% in Yoruba, this was not because they were safer, but because they failed to understand the prompts. Attack success rates increased for most models in the Nigerian languages, with GPT-4o Mini demonstrating the most significant cross-lingual safety discrepancy (+0.23 in Yoruba). When models did engage with adversarial prompts, many of the responses were harmful, with rates of harmful content reaching 0.63 in English and 0.50 in Nigerian Pidgin. The most difficult harm category to detect was cultural stereotypes and discrimination (ASR = 0.44 in Nigerian Pidgin). Comprehension in Yoruba was low across most models, and this directly suppressed apparent attack success without indicating actual safety. Gemini 2.0 Flash was the most consistent model across languages. Despite its explicit training in African languages, Aya 101 had the highest attack success rate in English (0.60) and one of the lowest Yoruba comprehension rates (0.28). These results demonstrate that English-centric safety alignment does not transfer to Nigerian languages, highlighting the urgent need for language-specific safety evaluations.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2411.14493

From Statistical Methods to Pre-Trained Models; A Survey on Automatic Speech Recognition for Resource Scarce Urdu Language

Muhammad Sharif, Zeeshan Abbas, Jiangyan Yi, Chenglin Liu

原文摘要

Automatic Speech Recognition (ASR) technology has witnessed significant advancements in recent years, revolutionizing human-computer interactions. While major languages have benefited from these developments, lesser-resourced languages like Urdu face unique challenges. This paper provides an extensive exploration of the dynamic landscape of ASR research, focusing particularly on the resource-constrained Urdu language, which is widely spoken across South Asian nations. It outlines current research trends, technological advancements, and potential directions for future studies in Urdu ASR, aiming to pave the way for forthcoming researchers interested in this domain. By leveraging contemporary technologies, analyzing existing datasets, and evaluating effective algorithms and tools, the paper seeks to shed light on the unique challenges and opportunities associated with Urdu language processing and its integration into the broader field of speech research.

cs.CL · cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.35826

Understanding Jev-Style System One Models: Does Structure Reduce Selection Bias?

Mingyang Song, Mao Zheng, Zhiyuan Ma, Xinpeng Zhou

原文摘要

Selection bias in large language models (LLMs) can persist despite instructions to ignore presentation order or prompts that elicit reasoning. Recent efforts to reproduce Jev-style System One behavior have produced a growing family of models that predict probabilities directly over supplied candidates. Yet systematic comparisons of selection bias across Jev versions, Jev reproductions, and generative LLMs remain limited in multi-option tasks. This leaves a central question: does Jev-style decision structure reduce selection bias? We address this question with a simple test that shuffles options while keeping question and candidate content fixed. Across two Jev versions, twelve Jev reproductions, and six generative LLMs, we trace individual answers through eight presentations and compare them with fixed-order repetition. On our primary collection of 1,700 questions from two benchmarks, Jev's accuracy varies by less than two percentage points, yet its cumulative failure set expands by 27.3-28.5% relative to the original order, with first failures continuing into the final presentation. Reordering loses substantially more initial successes than fixed-order repetition, a gap that also appears in highly repeatable Jev reproductions. Nor does Jev show a general advantage over the LLM baselines in preserving correct choices. Aggregation offers limited protection: voting yields modest gains for Jev, while even unanimous answers are frequently wrong. These results expose a gap between repeatable decisions and decisions that remain correct across equivalent presentations, showing why stable accuracy alone cannot establish resistance to selection bias.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.24033

Block-GTQ: RoPE-Block Rate Allocation for KV-Cache Quantization

Fengfeng Liang, Yuechen Zhang, Jiaya Jia

原文摘要

Larger models and longer contexts make the KV cache a memory and bandwidth bottleneck. We introduce Block-GTQ, a framework that uses the two-dimensional frequency blocks of rotary position embeddings (RoPE) to allocate cached-key precision. A blockwise logit-error bound motivates a label-free query-key energy score, which we combine with codec-dependent rate penalties. Under equal-cost budgets and diminishing marginal gains, largest-marginal-gain allocation exactly minimizes the separable integer proxy. We instantiate Block-GTQ with TurboQuant-MSE (TQ-MSE), grouping equal-rate blocks to support attention over packed caches without materializing a decoded fp16 KV cache. Across ten model configurations, K-only diagnostics reduce layer-averaged logit mean absolute error by about 32-80% relative to uniform TQ-MSE, improving all 367 layers at both 2- and 3-bit average logical key rates. At K2V2 (2 average logical bits per K/V coordinate) on Llama-3.1-8B-Instruct, Block-GTQ raises the six-task needle-in-a-haystack (NIAH) average from 70.6 to 97.4 and LongBench-EN from 33.7 to 44.9; K2V2 gains also hold on the tested 32B and 70B models. On DeepSeek-R1-Distill-Qwen-7B at K3V2, without fp16 sink or recent-token buffers, it achieves 49.6/38.8% avg@8 on AIME 2024/2025 versus fp16's 54.2/37.9%, where uniform TQ-MSE scores zero on both. On Qwen2.5-3B-Instruct, packed K3V3 serving on one H800 reduces resident KV footprint by a factor of 3.24 and retains perplexity close to fp16 at 128K, while uniform TQ-MSE degrades severely.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39519

Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity

Lu Sun, Yuheng Huang, Lei Ma, Zhijie Wang

原文摘要

Code embedding models have become a key building block for many software engineering applications, yet their internal representations remain poorly understood. Existing evaluations tend to focus on downstream task performance, offering limited insight into whether a single embedding can support both functional abstraction and implementation-sensitive analysis. To address this gap, we present a large-scale empirical study of 14 state-of-the-art code embedding models. We evaluate their representational behavior through three complementary analyses: supervised probing for functional abstraction and implementation fidelity, zero-shot retrieval experiments to assess geometric similarity, and controlled perturbation experiments that measure embedding responses to semantics-preserving code transformations. The results reveal a consistent abstraction-fidelity tension: models that better preserve stylistic and structural signals tend to do so at the expense of semantic generalization, while models with similar retrieval performance can nevertheless respond very differently to the same implementation changes. Overall, our findings suggest that a single universal code representation remains out of reach, motivating more representation-aware evaluation, selection, and deployment of code embedding models in software engineering.

cs.SE · cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36527

ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization

Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li, Kunyang Peng, Feng Xue, Shuai Wang, Kai Yu

原文摘要

Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form when their differences are not determined by speech. To our knowledge, ETC-Bench is the first and most comprehensive multilingual benchmark for evaluation-side transcript canonicalization, covering 181 phenomenon types across 12 languages. Each instance is a minimal pair that shares a sentence context and differs only in a target span exhibiting one phenomenon. To evaluate both canonicalization success and semantic preservation, we propose Semantic-preserving Exact-match Normalization Accuracy (SENA), which combines exact agreement between independently canonicalized pair members with a pair-relative BERTScore constraint against information loss. We further introduce the Taxonomy-guided Agent Canonicalization Skill (TACS), which provides LLM agents with phenomenon descriptions and explicit canonicalization contracts. Experiments with five baseline configurations and three TACS-based agents show that the agents outperform the baseline systems on shared languages. ETC-Bench provides a systematic testbed for evaluation-side transcript canonicalization across languages.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.16679

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Haolin Chen, Deon Metelski, Leon Qi, Tao Xia, Joonyul Lee, Steve Brown, Kevin Riley, Frank Wang 等 33 位作者

原文摘要

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $χ$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39464

Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM

Ryo Takizawa, Tempei Kabayama, Chiemi Yamazaki, Shun Kitamura, Ryo Matsuoka, Yuta Ando, Satoshi Kodera, Norihiko Takeda

原文摘要

View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A learned ensemble is a natural way to combine these outputs, but heterogeneous models typically require each output to be converted into a binary decision, probability, confidence score, or fixed-length feature vector. We developed a supervised large language model (LLM)-based late-fusion module that directly aggregates view-specific predicted finding statements and predicted measurements in language space and learns a case-level fusion function. In patient-level three-fold cross-validation of 859 examinations from 646 patients, the proposed method integrated heterogeneous outputs within a single framework, performed comparably to the best-performing reference strategy evaluated, and outperformed a general-purpose LLM without task-specific training. These results suggest that a supervised LLM can combine multiple upstream models without model-specific output conversion or feature engineering that requires medical knowledge.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.01993

SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning

Daeyong Kwon, Soyoung Yoon, Seung-won Hwang

原文摘要

Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SAFE, an LLM-as-verifier framework for evidence-grounded multi-hop QA. Rather than judging only the final answer after generation, SAFE verifies reasoning during generation by checking intermediate steps against the provided passages and previous reasoning trajectory. To make this process checkable, SAFE decomposes reasoning into atomic, evidence-grounded units represented with Knowledge Graph (KG) triples. At train-time, SAFE verifies benchmark supervision under KG-grounded constraints and constructs reliable verifier training data. At inference-time, an external verifier checks each generated step, identifies invalid reasoning, and provides correction feedback before errors propagate. Across three multi-hop QA benchmarks, SAFE improves accuracy by 8.8 pp on average. These results show that evidence-grounded multi-hop QA benefits from shifting LLM-based evaluation from post-hoc answer judgment to stepwise reasoning verification.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39433

ARBITRA: Robust Document-Level ATT&CK Extraction via Multi-Expert Argumentation

Youngjin Jin, Seungwon Shin

原文摘要

Cyber threat intelligence (CTI) reports describe adversary behavior in natural language, but converting them into structured MITRE ATT&CK mappings remains difficult: existing methods decompose reports to sentence-level granularity for extraction, while modern LLMs can work with full reports in a single pass but with noticeable performance degradation. We present ARBITRA, which orchestrates multiple role-specialized LLM experts that propose candidate ATT&CK entities from the full report, which are then verified through a per-candidate quantitative bipolar argumentation framework (QBAF) grounded in document evidence and rationales. We additionally construct reasoning-specialized corpora for fine-tuning so experts can act as effective participants during this verification process. Across ATT&CK extraction benchmarks, ARBITRA reaches a stronger precision-oriented operating point than sentence-level pipelines, recent LLM-based extraction systems, and frontier models including GPT-5.5. Under adversarial perturbations simulating conflicting TTP statements, cross-report contamination, and semantic poisoning, ARBITRA limits mean precision degradation to roughly half that of frontier-model baselines for a more robust extraction.

cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39419

Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

Guizhen Chen, Weiwen Xu, Wotao Yin, Anh Tuan Luu, Hou Pong Chan

原文摘要

Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it has counted. We argue that such failures, commonly attributed to perception, reveal a reference gap: the failure to bind language to the relevant visual entities, regions, or locations. Motivated by the theory of visual routines, we test whether external references such as numbering can narrow this gap. We introduce ReGap-Bench, a paired benchmark of five visual reasoning tasks in which the scene, question, and answer are fixed and only the reference varies. Results show that task-matched references improve accuracy by up to 25\%, while mismatched references provide little benefit or even hurt performance. These findings identify the reference gap as a bottleneck distinct from visual perception and show that constructing task-appropriate visual references can serve as a training-free visual skill for improving multimodal reasoning.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39417

Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent

Zhonghao Jiang, Xuyang Zheng, Yanfu Yan, Zhongxin Liu, Lingfeng Bao, Shuiguang Deng

原文摘要

Large language models (LLMs) have shown strong performance on software engineering (SE) tasks, driving the need for high-quality datasets for reliable training and evaluation. SWE-bench-style datasets (SWE datasets) are widely used to evaluate LLM-based coding agents on real-world software issues, where task clarity and test coverage directly affect whether instances are solvable and verifiable. However, quality issues persist in existing SWE datasets, and manual annotation is costly and labor-intensive, motivating LLM-based annotation. Existing approaches typically rely on static, overly general rubrics, limiting their ability to handle diverse and nuanced scenarios and often yielding high false positive rates. In contrast, human annotators draw on accumulated experience to make context-aware judgments. Inspired by this, we propose ExLabel, an LLM-based, self-evolving, experience-guided assistant for task clarity and test coverage assessment in SWE datasets. ExLabel maintains an evolving experience bank that distills cross-instance knowledge into stable yet adaptive judgment criteria and reuses relevant experience to guide the assessment of new instances. For systematic evaluation, we construct SWE-TQ, a new benchmark spanning eight programming languages, by cleaning human annotations from SWE-bench and Multi-SWE-bench. Experiments with three backbone LLMs show that ExLabel achieves the best F1 across all settings, with relative improvements of 44.2%/49.9% and 24.0%/18.4% over the best baseline for task clarity and test coverage assessment on the Python/Multilingual subsets, respectively. Moreover, a coding model fine-tuned on SWE-rebench data filtered by ExLabel resolves 66.2% of issues on SWE-bench Verified, outperforming the model trained on data filtered by the best baseline by 14.5%.

cs.SE · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39413

How Specific Do I Need to Be? Effects of User Query Underspecification on Deep Research Agents

Yi Wen, Xiangjue Dong, Bingxuan Li, Hangxiao Zhu, Leo Zhicheng Liu, Yu Zhang, James Caverlee

原文摘要

Deep research agents (DRAs) conduct long-horizon reasoning, search, and literature synthesis to provide long-form answers to complex, domain-specific questions. These agents are typically trained and evaluated on fully specified user queries. However, real-world user queries can often be underspecified. We introduce UNDERSPEC-DR, a framework for systematically evaluating how underspecified queries affect agents' final answer quality and intermediate search behavior. Across three DRAs we evaluated, underspecification substantially reduces how well DRA's answers fulfill users' information needs, even though they remain grounded in cited evidence. Our analysis of intermediate search behavior suggests a possible explanation: DRAs conduct broader searches that draw less on the original user query but rely more on their learned prior during training, which can be misaligned with users' intent. Our findings reveal the vulnerability of current DRAs to underspecified user queries and inform future efforts to build DRAs that proactively recognize when additional user input is needed to reliably complete deep research tasks.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29797

Metric-Dependent Annotation Saturation for Learning from Label Distributions

Guneet Kohli

原文摘要

When annotators disagree on a label, the disagreement itself carries signal - and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distributions subsampled from ChaosNLI, a dataset providing 100 independent annotator judgments per item, and identify metric-dependent saturation. In our 3-class NLI setting, entropy correlation - whether the model identifies which items elicit disagreement - requires N ~ 20-50 annotators to converge, while distributional match (KL divergence) saturates by N ~ 10 (87-95% of improvement across five model seeds); the specific thresholds are estimates for this setting, and it is the phenomenon, not the constants, that we expect to generalize. This finding rests on a prior observation: soft labels carry item-specific signal that label smoothing cannot replicate. Across five smoothing intensities, entropy correlation clusters at r ~ 0.45-0.49, while soft labels reach r = 0.643 (p < 0.001); per-item analysis traces this gap to smoothing's inability to distinguish ambiguous items from clear ones. The soft label advantage replicates across two architectures (DeBERTa, RoBERTa) and a non-NLI-pretrained baseline; differential saturation additionally appears in an exploratory cross-domain evaluation on content safety. These results suggest that annotation budgets should be informed by the target evaluation metric rather than set uniformly.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26676

Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows

Qian Xie, Wenyue Hua, Yueli He, Sripad Karne, Armaan Agrawal, Nikos Pagonas, Eugene Wu, Kostis Kaffes 等 10 位作者

原文摘要

LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometimes also considering latency. Finding good assignments incurs a separate search cost from evaluating multiple candidates. We introduce Cost-Coupled Gittins (CC-Gittins), a multi-objective extension of single-objective cost-aware Gittins search for Pareto recommendation. It exploits the coupling between evaluation and deployment costs: assignments that cost more to deploy also cost more to evaluate. The search alternates between seeking higher quality and lower deployment cost, reusing each evaluation to inform both searches. After each batch, CC-Gittins recommends assignments that are nondominated under uncertainty-adjusted estimates of quality and deployment cost. We evaluate CC-Gittins on eight quality--cost matrices from workflows with two to five roles and up to 1,681 candidate assignments. We also evaluate the method with latency as a third objective. Across the eight benchmarks, CC-Gittins recovers a substantial fraction of the true Pareto frontier at roughly 10% of the exhaustive-evaluation cost, and recovers most of the frontier with few false positives by 30%.

cs.LG · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39398

Robustness of Chatbot LLM Judgments of Presidential Actions and Hypothetical Reforms

Oleg Vasilyev

原文摘要

Chatbots are increasingly consulted about public affairs, and their judgments of policies are useful only if they are robust. We measure this robustness in the setting of an ordinary user, through consumer chat interfaces. For 30 days, five chatbot configurations (Mistral, Gemini Flash, Claude Sonnet, and Claude Opus at two effort settings) were asked twice a day to score the long-term effect on the United States of 40 actions of the last four presidential administrations and of 15 hypothetical reforms, each with a confidence and a short comment. The judgments are robust: all configurations agree on the sign and the ranking of the administrations' mean scores, and two different configurations asked on the same day give opposite signs to the same action in about 4% of cases. Responses from different days differ more than same-day responses, but the difference grows slowly over the month, except where the service itself changed. We identify three such changes, which shifted the judgments while leaving little or no trace in the interface. Treating the comments as a retrieval task, we find them specific to each item and consistent across runs and chatbots, with lexical and embedding similarities agreeing. We release the dataset of 16,500 judgments.

cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.02959

The Direction of Ignorance: LLMs Encode and Temper a Unigram Prior

Toni J. B. Liu, Jiajun Bao, Gurbir Arora, Mitchell Ostrow, Yizhou Liu, Raphaël Sarfati, Nicolas Boullé, Christopher J. Earls

原文摘要

What does a language model predict when it has few clues?The answer lies in its unembedding geometry: a single direction of the unembedding matrix encodes the unigram distribution of the training corpus, which serves as the Bayesian prior the model falls back on when uncertain. This structure, termed the direction of ignorance, appears across all model families examined (Llama, Qwen, Gemma, and Pythia), ranging from 0.4B to 405B parameters. Projecting the final prediction state onto this direction yields a per-token prior loading factor $λ$, which declines steadily as the context becomes more informative. Formally, the same projection decomposes the prediction state into two orthogonal vectors interpretable as the two components of a tempered Bayesian update: a unigram prior raised to the exponent $λ$ and a context-driven likelihood. This geometric probabilistic connection makes $λ$ meaningfully comparable across model sizes and families. Larger models generally exhibit lower prior reliance, and reasoning models exhibit lower reliance than their base counterparts. Finally, we show that $λ$ serves as a causal, inference-time control: reducing it can promote context-driven continuations and improve Llama-3.2-3B-Instruct on GSM8K, whereas amplifying it or applying matched perturbations along random directions degrades performance.

cs.LG · cs.AI · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39373

What Makes Medical Examination Items Difficult? Using Large Language Models to Explore Patterns Associated With Empirical Item Difficulty

Xiaomeng Xiong, Marcus Walker, Yanlin Jiang

原文摘要

Research on medical item difficulty has largely focused on prediction rather than on identifying interpretable patterns associated with empirical difficulty. This study used empirical difficulty labels to guide large language models (LLMs) in inducing difficulty rubrics and examined how rubric guidance affected LLM difficulty judgments. Using training items and their empirical difficulty estimates from the United States Medical Licensing Examination (USMLE) and the Physician Assistant National Certifying Examination (PANCE), Claude Opus 5 induced separate rubrics for absolute and pairwise difficulty judgment. None of the induced rubrics treated surface features, such as stem length, option count, or images, as major sources of difficulty. Several patterns emerged across both examinations, including cue convergence, misleading cues, and option competition, although their specific forms differed. Retrieval of knowledge that could not be derived from the stem was particularly prominent in the PANCE rubrics, whereas the USMLE rubrics placed greater emphasis on integrating multiple clinical cues. We compared commercial and open-weight LLMs on held-out items under unguided and rubric-guided conditions. Rubric guidance changed how models used the difficulty scale but did not consistently improve performance. In absolute judgments, guidance encouraged broader use of the scale and generally improved coarse-grained agreement, without consistently improving rank ordering. In pairwise comparisons, its effects varied across models and examinations, and judgments became more sensitive to presentation order. These findings suggest that the value of label-guided rubric induction may lie more in generating interpretable, testable hypotheses from empirical difficulty data than in reliably improving difficulty judgments.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39372

Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models

Chengwei Zhou, Zhaoyan Jia, Massoud Pedram, Gourav Datta

原文摘要

The decoding order of masked diffusion language models (dLLMs) can substantially affect generation quality, yet common decoders typically apply the same reveal rule throughout generation. Confidence provides a strong default, but it measures how decisively a position can be predicted now, not how useful revealing that position will be for subsequent decoding. We propose Cord, a lightweight prompt-conditioned policy that retains confidence decoding as a stable reference and learns when and how to depart from it through geometric residuals over generation direction, proximity to revealed context, and two-sided infilling. The residuals adapt to both the prompt and the evolving partial response. Rather than sampling a new policy action at every decoding step, Cord samples a single low-dimensional coefficient matrix per rollout, which induces an entire state-dependent reveal trajectory. This yields a contextual-bandit formulation trained directly from sequence-level rewards, without step-level credit assignment or backbone updates. Across three dLLMs and five reasoning, code, and constraint-satisfaction benchmarks, Cord improves average task success from 32.0% under confidence decoding to 48.2%, and further improves over the best per-domain fixed residual. Behavioral audits show that the learned residuals induce substantial, task-dependent changes in reveal locality and two-sided infilling. Cord adds only $0.53$M trainable parameters, requires no additional backbone forward passes, and incurs only 5.39% inference latency overhead.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33005HF 社区推荐

OpenEBFM: Energy-based Foundation Models Are Scalable Architecture

Yuan Pu, Yudong Lu, Ting Wang, Zhicong Hong, Qinuo Li, Xuansheng Wu, Na Zou, Xia Hu 等 9 位作者

原文摘要

Energy-based models have shown promising properties for domain-specific tasks but remain challenging in modeling general-purpose scenarios. To bridge this gap, we design energy-steered models (ESMs) for foundational language modeling. ESMs integrate energy steering and token generation within a single architecture to leverage the energy-guided search to refine token generation. Specifically, ESMs first optimize a latent state over the energy landscape, then leverages the refined latent state for token generation. By performing such energy-guided pre-training on large-scale corpora, ESMs learn generally effective energy landscape where favorable tokens correspond to lower energy values. To explore the scaling behavior of ESMs, we pre-train ESMs on three large-scale corpora, then evaluate across 26 downstream tasks spanning a broad range of domains. Our results demonstrate that ESMs have promising scaling behaviors with increasing model size and training data, and outperform GPTs on most downstream tasks. These findings highlight ESMs as a promising architecture for large-scale pre-training and general purpose problem solving. We fully release the model weights and training infrastructure to enable the community to completely reproduce and extend our results. GitHub: https://github.com/datamllab/openebfm HuggingFace: https://huggingface.co/collections/guan-wang/openebfm

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.04565

Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories

Xuebin Li, Hanqing Zhao, Siyuan Liang, Kejiang Chen, Weiming Zhang, Dacheng Tao, Nenghai Yu

原文摘要

LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking. Prior work on search-agent safety primarily focuses on static web-content injection, but modern agents issue follow-up queries and cross-check competing sources, so a single injected page is often diluted or rejected. We show that the channel delivering search and page observations is a fragile security boundary: beyond exposing the agent to a single poisoned page, a mediated search interface can repeatedly steer how the agent gathers evidence and forms its final answer. Under a constrained tool-intermediary threat model, appending only one controlled result per query can substantially increase attack success when the evidence is coordinated across the agent's trajectory. We study this setting with a strategy-driven long-horizon attack system and introduce Authority-Chain Hijack (ACH), an expert-refined strategy that turns isolated search-result and page-content manipulations into a coherent evidence chain across seemingly corroborating sources. ACH achieves the highest Overall ASR among all baselines, reaching 55.9% / 83.3% ASR / MaxN ASR on the full SafeSearch test split. We further introduce Trace-Guided Strategy Evolution (TGSE), which automatically improves attacker strategies from execution traces, replacing manual redesign with trace-driven refinement; its strongest single setting reaches 71.4% / 95.0% in held-out evaluation. Code is available at https://github.com/MBOSSLESS/Breadcrumbing-Search-Agents.

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39339

Does the Citation Matter? Quality, Grounding, and Physician-Rubric Accuracy of Google's AI Overviews for Medical Information

Sam Agnoli, Brigid Reilly, Lily Barna, Emőke-Ágnes Horvát

原文摘要

Google's AI Overviews (AIOs) are the first result users encounter when searching the web, shifting the work of selecting and evaluating sources from the user to Gemini. This may be especially consequential for health information, given that Google's traditional algorithm was designed to prioritize quality sources, and inaccurate information carries health risks. We evaluated 3,611 benchmark health questions, comparing each AIO against that question's top five traditional results on source selection and quality. We also evaluated the AIOs' statement grounding in their cited sources and how accurate AIOs were against physician-written rubrics. Overviews appeared for 96.4% of questions but drew on substantially different evidence than traditional search: only 44.4% of the top five results were cited by the corresponding AIO, which instead overrepresented commercial health publishers (e.g., WebMD, Healthline) at the expense of academic and government sources (e.g., Cleveland Clinic, National Health Service). AIO-cited pages scored lower than traditional results on four of six well-established credibility criteria. The grounding of AIO statements to their sources was poor: after correcting for classifier error, an estimated 56.7% of cited statements were supported by their cited page, and a further 20.8% of all statements were factual claims with no citation at all. When AIOs were graded against physicians' rubrics, they earned 38.2% of all available points (e.g., accuracy 54.2%, completeness 21.6%), and among the subset of AIOs whose physician rubric anticipated a specific inaccurate or potentially harmful claim, 22.2% of AIOs contained the harmful content. Notably, the accuracy of AIOs was unrelated to the grounding of their statements. We recommend AIO literacy interventions for users and holding AIOs at least to Google's own health-ranking standards.

cs.IR · cs.CL · cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33775

The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS

Haggai Roitman

原文摘要

Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine decisions (routing, gating, scoring, classification) that modern AI systems require at sub-second latency. A growing class of models addresses this gap: System 1 decision models, architectures that map an input directly to a typed, structured decision in a single forward pass. This guide provides a comprehensive, practitioner-oriented treatment of the field. We propose a five-family taxonomy covering encoder-based classifiers, reward models, non-autoregressive decision engines, contrastive decision models, and extraction models, and we provide in-depth coverage of each family's architecture, training methodology, and deployment trade-offs. A central theme is calibration: we develop the theory of proper scoring rules, analyze Reinforcement Learning for Calibrated Decisions (RLCD), and examine recently discovered phenomena including IIA violations, ordinal-scale bias, and few-shot recalibration under distribution shift. On the integration side, we describe how System 1 models serve as decision infrastructure within agentic workflows and System 1 + System 2 cascades that route between fast and slow models based on calibrated confidence. The guide covers 18 application domains, maps the rapidly growing open-source ecosystem (over 70 model reproductions in weeks), provides runnable code throughout, and includes a practitioner's checklist, an open-source model zoo, and 22 self-assessment questions with detailed answers. Spanning 190 references, it is intended as a unified entry point for researchers and engineers working at the intersection of fast decision-making, calibration, and production AI systems.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39308

Unlimited OCR Works 2

Shu Wei, Jingjing Wu, Qunyi Xie, Lingshu Zhang, Xiangcheng Du, Yannian Fu, Mengjie Wang, Zuyi Wang 等 12 位作者

原文摘要

Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual context grows substantially, sharply increasing the computational cost of each decoding step and limiting the scalability of ultra-long document parsing. Inspired by human book transcription via localized focus without re-scanning preceding pages, we introduce Unlimited OCR 2, a document parsing model that looks only at what it transcribes. Building on Unlimited OCR, we upgrade all the decoder attention modules to Sparse Reference Sliding Window Attention (SR-SWA), bounding active reference tokens to a fixed capacity and thus sustaining constant computational costs across arbitrarily long documents. By combining SR-SWA with Unlimited-Horizon Decoding Paradigm, Unlimited OCR 2 enables document parsing over virtually unlimited lengths without prohibitive memory overhead. At the hundred-page scale, Unlimited OCR 2 achieves 7.0$\times$ and 5.6$\times$ per-step speedups over Full Attention and R-SWA, respectively. Furthermore, it delivers state-of-the-art end-to-end performance on both MPDocBench and MarathonDocBench, our newly proposed benchmark targeting hundred-page document parsing. Ultimately, the capacity for uninterrupted, one-shot document parsing signifies a fundamental paradigm shift into the OCR 3.0 era.

cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.06540

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Zhenyu Liu, Xuanyu Zhang, Yunxin Li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Minjun Zhao, Fanbo Meng 等 13 位作者

原文摘要

Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, revealing that modality interference arises from inherent gradient conflicts between acoustic and semantic modeling when the two modalities are forced to share a deep parameter space. Guided by this key insight, we introduce Lychee-FD, a native end-to-end full-duplex framework designed to mitigate modality interference. Importantly, we propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. Extensive experiments on multiple full-duplex benchmarks demonstrate that our method significantly advances the state of the art, yielding substantial improvements in both speech intelligence (+7.4% on Spoken QA) and full-duplex interaction fluidity (+28.5% on FullDuplexBench 1.5) without compromising inference efficiency. To the best of our knowledge, this work is the first to achieve two key advances: 1) uncovering and elucidating the root cause of modality interference in full-duplex SLMs, and 2) designing an elegant hierarchical model together with a practical solution for seamless, high-performance, native intelligent full-duplex SLMs.

cs.CL

查看论文
arXiv ↗PDF ↗