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

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 02:49 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 03:23 — 2026-11-14 03:23（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：2026-11-14 02:49最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,727 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 3,930 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 02:48（北京时间）
版本更新 · v2arXiv:2606.20910

Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents

Dayeon Kang, Hyejun Jeong, Jade Sheffey, Pubali Datta, Amir Houmansadr

原文摘要

As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and security challenge. Existing defenses, such as robots.txt and active bot-blocking, are insufficient, as they are widely violated and easily circumvented. In this work, we demonstrate that AI web agents can be effectively distinguished from humans and traditional crawlers using a multi-layer fingerprint based on both network layer characteristics (e.g., TLS, HTTP) and browser interaction behavior. We implement this mechanism as a programmatic logging framework that can be deployed on a live, instrumented domain. By analyzing six prominent agent frameworks (AutoGen, Browser Use, Claude, Gemini, ChatGPT, and Skyvern), we uncover latent structural differences in how these systems assemble HTTP requests, establish TLS/HTTP connections, and execute autonomous browser actions. Feeding these multi-layer features into a decision tree classifier, our framework achieves high-fidelity identification (100% accuracy), successfully isolating distinct agent architectures and differentiating agent traffic from both human browsing baselines and legacy crawlers. Our findings demonstrate that cross-layer agent tracking provides a robust approach to content protection and web security policy enforcement.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15680

SpaceMCP: Vision Language Model Spatial Reasoning via Model Context Protocol

Ameen Izhac, Nobuko Yoshida, Ronald Clark

原文摘要

Despite impressive advances in large language models (LLM), vision-language models (VLM) still exhibit limited spatial reasoning capabilities. Recent progress in feed-forward 3D reconstruction has enabled precise, real-time geometric understanding from visual inputs. In this work, we propose SpaceMCP, a framework that leverages these advances to introduce an MCP-style paradigm for spatial reasoning. Our approach augments a VLM with structured function calls, allowing it to query a scene graph for spatial information such as distances, object positioning, and camera properties. The scene graph is constructed in real time using feed-forward 3D reconstruction to recover metric geometry, combined with open-vocabulary segmentation to identify and localize relevant objects within the scene. Paired with the VLM's strong reasoning capabilities, the VLM is able to combine this primitive information to solve more complex spatial tasks. Without any training, SpaceMCP achieves state-of-the-art results on VSI-Bench, MMSI-Bench and VSTI-Bench, outperforming recent spatially post-trained VLMs and improving its base VLM by 15-22 points per benchmark. We argue that, given the contrast between the relatively slow progress in native VLM spatial reasoning and the rapid advances in feed-forward 3D computer vision, this paradigm offers a promising path forward for enabling robust spatial reasoning.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15651

Recover, Don't Just Continue: Learning from Feedback for Physical Failure Understanding and Correction

Miao Pan, Kaixiang Yao, Xiaohe Zhou, Xu Wang, Qinfeng Li, Wenqi Zhang, Xuhong Zhang

原文摘要

Multimodal large language models are regarded as the cognitive foundation of embodied intelligence, but planning from instructions alone cannot make them reliable. During execution, actions deviate from intended effects, constrained by the embodiment and environment. An embodied brain must understand why execution deviates, identify what can be reliably realized, and revise decisions using interaction experience. These correspond to causal failure localization, capability-constrained adaptation, and experience-driven revision. Current embodied foundation models largely lack these capabilities. To address this, we introduce Embodied-Corrector. We construct failure-recovery data by injecting perturbations at subtask boundaries of successful trajectories, replaying affected subtasks, and keeping failures that are observable from public evidence and recoverable from the current state. We align actions, consequences, failure causes, and recoveries into Judge-Cause-Sub-Fine supervision. Training uses evaluation-first SFT: the model learns Judge and Cause first, then Sub and Fine conditioned on accurate prefixes. Since deployment uses self-generated prefixes, evaluation errors propagate into recovery planning, and response-level rewards are too coarse to locate affected planning tokens. We therefore use OPD to internalize the planning distribution under accurate prefixes into that under self-generated ones: the model generates plans from self-generated prefixes, while a contrastive forward pass with accurate prefixes compares token probabilities to reinforce or suppress planning tokens. At deployment, this branch is removed. Experiments show stronger failure analysis and corrective planning: with a frozen VLA, composite task success improves by 6.1 percentage points; with fixed GPT-5.5 execution, manipulation and navigation tasks improve by 13.9 percentage points.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00828

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models

Okan S. Coskun, Florian Rottach, Carsten Eickhoff, William Rudman

原文摘要

We investigate the geometry of decision-making in Multiple Choice Question Answering (MCQA) through the lens of isotropy. Analyzing five open-weight models across diverse datasets, we identify decision-critical transition layers characterized by a shift in isotropy, coinciding with a major representational change and the emergence of task-relevant clusters. We demonstrate that this synchronized geometric behavior is strongly correlated with downstream accuracy ($r\approx0.84$), displaying its relevance for successful decision-making. Furthermore, we show that this transition is robust to prompt variations, suggesting that it reflects a general mechanism of model behavior.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.10947

The Platonic brain bridge hypothesis: brain networks as architectural priors for multimodal large language models

Pengfei Zhang, Biao Tian, Xiangang Li, Li Liu

原文摘要

Multimodal large language models predict brain activity, but alignment has remained a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, which jointly process video, audio and text, share brain-like representations usable in both directions. From model to brain, seven omni models show stable brain-likeness across participants, and our encoding experts lead the Algonauts 2025 out-of-distribution leaderboard by mean score. From brain to model, we make three contributions. Brain-MoE ties the experts of a frozen model to the seven cortical networks, raises held-out accuracy in all 15 model-benchmark pairs and exceeds capacity-matched random experts in 14. Brain-AVQA, to our knowledge the first audiovisual benchmark with cortical-network labels for every question, supplies the pretraining questions. Brain-Scope finds sparse features that predict brain responses, steer routing and, when removed, weaken brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.

q-bio.NC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11482

Evaluating Local Language Model Agents for Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

Jorge García-Carrasco, Javier Sanchis, Alejandro Reina-Reina, Alejandro Maté, Juan Trujillo

原文摘要

Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasise textual responses or isolated code rather than complete engineering artifacts. Objectives: We evaluate whether local LLM agents can produce correct and reliable data-engineering artifacts, isolate the contribution of a closed-loop workspace and of input-structure knowledge, and examine trade-offs in runtime, cost, and failure behaviour. Methods: We introduce a benchmark of fifteen mobility data-engineering tasks with deterministic checkers for the scripts, tables, structured files, figures, and reports they produce. Sixteen configurations from six model families are evaluated in three conditions (chat-only, chat-schema, agent-with-tools) with five repetitions per model, condition, and task, yielding 3,600 scored attempts on a consumer-grade GPU. Results: A 4-billion-parameter model at 4-bit reaches 77.3%, a 9-billion-parameter model 80.0% within about 6.5 GB, and a 12-billion-parameter model from another family 81.3%, against 98.7% for the highest-scoring configuration, which solves 14 of 15 tasks in all five repetitions. Above two billion parameters the workspace loop raises pass rates by 24.0 to 65.3 points over uninformed one-shot generation, and its contribution exceeds that of the input-structure summary in eleven of fifteen tasks. Conclusion: Open-weight models that fit on one consumer GPU support a meaningful share of data-engineering work once given a workspace loop, although capability still separates usable from unusable configurations and high-stakes outputs need validation. Being mobility-specific and checker-based, the benchmark characterizes the evaluated configurations, not all data-engineering practice.

cs.SE · cs.AI · cs.DB · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.03217

An Asymptotic Theory of Chain-of-Thought in In-Context Learning

Kaito Takanami, Cengiz Pehlevan

原文摘要

Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermediate reasoning steps at inference time. Yet the scaling behavior of generalization with CoT depth remains poorly understood. To address this question, we study a theoretically solvable model of CoT for in-context weight prediction in linear regression, where test-time reasoning is represented as an iterative refinement of the weight-parameter estimate. Using tools from random matrix theory under high-dimensional asymptotics, we derive an exact formula for the generalization error as a function of reasoning depth, pretraining data amount, and context length. Our analysis reveals a sharp phase transition separating exponential and polynomial improvement, saturation, and overthinking, and characterizes how the optimal reasoning depth scales. We further show that deeper reasoning is most effective with sufficiently rich pretraining and in-context information, whereas limited pretraining or context makes longer reasoning prone to error amplification or saturation. We also validate these predictions through experiments on fully learned linear attention and softmax attention models. Our results provide a unified theoretical account of how test-time CoT depth affects generalization.

stat.ML · cond-mat.dis-nn · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15600

MemCredit: From Relevance to Utility for Decision-Time Memory in Long-Horizon Web Agents

Quanjiang Guo, Sijie Wang, Qianyang Zhu, Ben Zhang, Jinchuan Zhang, Ke Yan, Zhao Kang

原文摘要

Large language model (LLM) agents increasingly operate over long Web interaction histories, making memory management critical for reliable and efficient decision making. Existing methods primarily optimize storage, retrieval, or compression, but the memories most semantically relevant to the current state are not necessarily those that most improve the agent's action. We introduce MemCredit, a decision-centric memory framework that shifts memory selection from semantic relevance to decision utility. MemCredit estimates the state-, reference-context-, and policy-conditional marginal contribution of individual memories through controlled counterfactual interventions, and distills these intervention-derived credits into a lightweight utility estimator. At inference time, semantic relevance is used only for high-recall candidate generation, while predicted utility arbitrates which memories are retained under a fixed token budget, without modifying the underlying agent policy or requiring additional environment interaction. We evaluate MemCredit on ALFWorld and WebShop against representative memory baselines. On ALFWorld, MemCredit achieves 86.57 SR@50 under a 500-token historical-memory budget, compared with 65.67% for BM25 retrieval. Counterfactual analysis further shows that memory utility is sparse, strongly state dependent, and poorly captured by semantic relevance. These results suggest that decision utility provides a more effective principle than relevance alone for long-horizon agent memory management.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2412.16555

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models

Yanxu Mao, Peipei Liu, Tiehan Cui, Zhaoteng Yan, Congying Liu, Datao You

原文摘要

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly severe. Jailbreaking attacks, as an important method for detecting vulnerabilities in LLMs, have been explored by researchers who attempt to induce these models to generate harmful content through various attack methods. Nevertheless, existing jailbreaking methods face numerous limitations, such as excessive query counts, limited coverage of jailbreak modalities, low attack success rates, and simplistic evaluation methods. To overcome these constraints, this paper proposes a multimodal jailbreaking method: JMLLM. This method integrates multiple strategies to perform comprehensive jailbreak attacks across text, visual, and auditory modalities. Additionally, we contribute a new and comprehensive dataset for multimodal jailbreaking research: TriJail, which includes jailbreak prompts for all three modalities. Experiments on the TriJail dataset and the benchmark dataset AdvBench, conducted on 13 popular LLMs, demonstrate advanced attack success rates and significant reduction in time overhead.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15575

Does Confusing Code Confuse LLMs? A Pilot Study on C++

Tim van de Wetering, Lola Solovyeva, Fernando Castor

原文摘要

Large language models (LLMs) are increasingly deployed for software maintenance tasks that depend heavily on code comprehension. While atoms of confusion, minimal code patterns empirically shown to impair human program comprehension, are well studied, it remains unclear whether these same patterns affect LLMs, and whether their impact varies across maintenance tasks. We present a pilot study evaluating the impact of atoms of confusion on LLM performance on C++ code drawn from three production libraries, using ChatGPT and GitHub Copilot on three software development tasks: atom injection and removal, output prediction, and code explanation. Our results reveal three preliminary findings: (i) the impact of atoms on LLMs is strongly task-dependent; (ii) atoms requiring reasoning about surrounding code are the most resistant to transformation, while localized syntactic atoms are handled reliably; and (iii) LLMs remove atoms of confusion more reliably than they inject them, suggesting that removal succeeds through pattern matching while injection requires deeper comprehension.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.24763

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker

原文摘要

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward networks across tasks, which can entangle task behavior and make controlled capability expansion difficult. Sparse Mixture-of-Experts (MoE) decoders provide conditional computation, but token-level learned routing is not naturally aligned with task-level procedural objectives. We propose MoTE (Mixture of Task Experts), a decoder architecture that converts large language model feed-forward networks into task-specific experts while keeping the multimodal backbone shared. Each example follows one sample-level task route, so active task-expert computation remains independent of the number of stored task experts. We instantiate this design as VideoLLM-MoTE and evaluate it on five COIN benchmarks using explicit task routes. The five-expert model activates ~2B LLM parameters per sample and achieves higher average top-1 accuracy than recent VideoLLM baselines. Under the same expert topology, it improves over dense all-expert activation and learned sparse-routing controls. These results show that task-structured routing provides an interpretable and compute-efficient decoder alternative for multi-task video-language learning.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03767

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction

YuJie Liu, Dezhen Xue, Jun Sun, Xiangdong Ding, Zhibin Gao, Turab Lookman

原文摘要

General-purpose Large Language Models (LLMs) increasingly rival domain-specific pipelines on scientific prediction, but their performance under distribution shift is untested. Across six alloy and crystal-structure datasets, we benchmark LLMs against traditional, BERT-based, TabPFN, and text-regression baselines under random cross-validation and six out-of-distribution (OOD) protocols shifting input and target distributions, with severity quantified via a standardized Wasserstein distance. We isolate the LLM's advantage over k-nearest-neighbor (k-NN) retrieval: it beats k-NN on all eight tasks at a fixed 5% reference budget, on seven of eight when independently optimized, and in 72.5% of 120 OOD task--protocol configurations against an optimized baseline. No model family is uniformly best; the LLM is often strongest under severe shift, and error increases with target-space but not representation-space severity. Self-reported LLM confidence tracks both shift and error, more consistently than a density-only control from the same retrieved samples, and a matched-cohort check finds no substantial evidence of memorization.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13217

Reliability of Claude Code as an Agentic AI Grading System for Handwritten University Exams

Rayed AlGhamdi

原文摘要

This study examines the reliability of Claude Code, an agentic deployment of the Claude Opus 4.6 large language model, as a grading system for handwritten university exams. Four research questions addressed agreement with expert human grading on total scores (RQ1), agreement across five question types from multiple choice to evaluative judgement (RQ2), consistency across two independent grading sessions one week apart (RQ3), and the accuracy of AI-generated feedback (RQ4). Claude Code graded the 20-mark mid-term papers of 60 consenting students in a Saudi computer graphics course in a single agentic session, guided by three rubric files. Reliability was estimated on disjoint samples: 20 papers for RQ1, RQ2 and RQ4, and 15 papers for RQ3. Analyses used Pearson correlation, mean absolute error, Bland-Altman analysis, weighted Cohen kappa, intraclass correlation, and a four-category coding scheme separating diagnostic from confirmation feedback. The author, as the sole subject-matter expert for the course, provided the human benchmark, so the design assesses agreement with a domain-expert reference rather than inter-rater reliability. AI grading agreed strongly with human grading on totals (r = 0.97; MAE = 0.85 marks) with a small but significant AI-positive bias of 0.68 marks, showed excellent test-retest consistency (ICC = 0.96), and produced accurate feedback (92.8% diagnostic; 97.8% confirmation). Drawing items were the outlier on three of four measures. Three failure modes recurred: keyword matching without conceptual depth, selection-state ambiguity on corrected multiple-choice answers, and region-of-attention drift on hand-drawn diagrams. The findings suggest that AI grading at this capability level can assist instructors on objective and short-form items under structural safeguards but is not yet ready to replace instructor judgement at boundary cases or on drawing items.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15506

KernelAudit: Contract-Aware Auditing of Validators for LLM-Generated GPU Kernels

Ziyuan Li, Zihe Song, Xiaofang Qi, Wei Yang, Tao Xie

原文摘要

The effectiveness of generating GPU kernels driven by a large language model (LLM) is highly dependent on the quality of the used validator (used to accept or reject a generated kernel candidate against the contracts of the given kernel-generation task), whose results inform reward assignment, candidate selection, and speedup claims during kernel generation. However, an existing validator suffers from various limitations, e.g., wrongly accepting a candidate due to missing its forbidden library use or wrongly rejecting a candidate due to determining its permitted library use as forbidden (constraints on library uses are stated in the task contracts). To assess the quality of a validator against the given task contracts, we propose an independent-audit approach for the validator by (1) construction of audit oracle: labeling a candidate as PASS or FAIL based on three separate dimensions in our proposed contract model (i.e., semantic correctness, implementation integrity, and measurement integrity) and (2) auditing of the validator against the audit oracle: comparing the labels of the candidate against the validation results produced by the validator. For semantic correctness, reference-calibrated stress tests check output correctness on valid inputs for a candidate. For implementation integrity, reference and candidate execution traces are used to determine specific library uses. For measurement integrity, timing checks assess whether the reported runtime reflects the full time needed to complete the candidate's computation. We apply our approach to assess the quality of six validators and 716 candidates from seven corpora, including constructed controls. The evaluation results show that our approach helps assess the existing six validators to have nontrivial false-reject rates. There is high-degree agreement between the candidate labels produced by our audit oracle and human judgments.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15493

The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy

Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Cong Qin, Binbin Zheng, Chaowen Hu, Zekai Shao

原文摘要

Reinforcement learning with verifiable rewards has shifted the alignment paradigm of large language models from subjective preference to objective correctness, yet a fundamental disconnect persists between exploration diversity and reasoning validity. Existing strategies predominantly rely on "blind" entropy metrics, e.g., token-level or global sequence-level entropy, which structurally fail to distinguish between effective reasoning and potential hallucinations. This misalignment creates an illusion of diversity, where high entropy tends to signal chaotic degeneration rather than valuable exploration. To bridge this gap, we introduce Effective Entropy, a validity-aware entropy concept that quantifies diversity exclusively within the valid subspace and systematically filters out the noise of incorrect trajectories. Built on this concept, we instantiate VEPO, a simple Validity-aware Entropy Policy Optimization method that directly incorporates effective entropy into RLVR training. VEPO induces an adaptive attraction dynamic that drives up the probability of under-explored valid trajectories, a mechanism that matches the practical regime of large-scale autoregressive models where sequence probabilities remain extremely small. Experiments on six mathematical reasoning benchmarks with 1.5B and 7B DeepSeek-R1-Distill-Qwen models show consistent aggregate accuracy gains over GRPO and competitive repeated-sampling success. A direct evaluation with matched correct counts finds more distinct strategies on commonly solved MATH500 problems, supported by paired statistical tests and three-seed training comparisons.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.16543

The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation

Jiaheng Zhang, Daqiang Zhang

原文摘要

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation.

cs.IR · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15449

Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning

Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim

原文摘要

Text-aware image super-resolution (TAISR) aims to recover high-resolution images from low-resolution inputs while preserving textual content. Existing methods treat this as a visual restoration problem, yet severely degraded text often cannot be read from local visual evidence alone. Humans instead read it by reasoning over image context, logical patterns, and prior knowledge. This raises a fundamental question: Does TAISR need reasoning? To answer this, we introduce two diagnostic tools. The first, ReasonText, is a human-curated benchmark that separates reasoning-required text from locally recoverable text. The second, Ground-Truth Text-Crop Accuracy (GTTCA), is a recognition-based metric that measures text restoration quality without text detection errors. Evaluating twelve recent super-resolution (SR) models, we find a consistent and substantial performance drop on reasoning-required text, revealing a systematic blind spot. Two observations point to a remedy. One is that text-conditioned SR models restore text substantially better when given ground-truth text. The other is that multimodal large language models (MLLMs) can read degraded text in low-resolution images through reasoning. We therefore propose Reasoning Transfer via Captioning (RTC), a training-free plug-in that uses an external MLLM to infer the degraded text and feeds the resulting caption to a text-conditioned SR model. RTC consistently improves all six text-conditioned SR models we evaluate, especially on reasoning-required text. Surprisingly, a real-world SR model with RTC can even outperform the TAISR model with RTC, suggesting that reasoning should be a core design axis for future TAISR.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15448

Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models

Nikola Đukić, Tim Lebailly, Tinne Tuytelaars

原文摘要

In computer vision, vision-language and self-supervised encoders are two unique paradigms characterized by global language alignment and high-quality vision-only patch representations, respectively. Multimodal large language models (MLLMs) often use the former because of language alignment, despite the recent rise in vision-centric tasks resembling traditional dense vision tasks that would likely benefit from the high-quality patch representations, raising the question whether self-supervised models could aid MLLMs in vision-centric tasks. To investigate this, we define semantic (in)consistency of patch tokens from language-aligned encoders and identify two sets of tokens, semantically consistent (SCTs) and semantically inconsistent (SITs). Through systematic probing via the removal of SCTs or SITs from the input of modern MLLMs, we show higher reliance on SCTs than SITs, as removal of the former induces larger performance drops. This demonstrates that MLLMs benefit from semantic consistency of vision tokens. With this in mind, we devise a simple yet effective extension of the MLLM training objective that combines traditional language modeling with semantic guidance via minimization of semantic inconsistency. This strategy, named Semantically-Guided Training (SGT), combines the signals of both loss terms to push the vision encoder towards providing semantically consistent tokens, while preserving language alignment. Extensive evaluation shows that SGT outperforms all baselines and MLLMs with specialized vision encoders on vision-centric benchmarks while keeping strong scores on text-centric benchmarks, thus setting state of the art on average across all tasks. Our results highlight the importance of combining language alignment and semantic consistency through the lens of MLLMs rather than independently from them and pave the way towards the design of better MLLM vision encoders.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2502.21037

The amplifier effect of artificial agents in social contagion

Mingmin Feng, Eric Hitz, Luca Lazzaro, Radu Tanase, René Algesheimer, Manuel S. Mariani

原文摘要

Individuals and organizations increasingly consider delegating decision-making to AI agents, which may significantly alter social contagion dynamics. We ask whether artificial agents exhibit different adoption thresholds from those of human subjects when making decisions and, if so, how such differences may affect the spread of social contagions. To answer these questions, we conduct two choice experiments - recently administered to human participants - with artificial agents powered by large language models (LLMs). Across two domains and five LLMs, artificial agents exhibit systematically lower adoption thresholds than human subjects. Simulations of diffusion calibrated with the experimental findings show that, holding network structure fixed, even a modest share of artificial agents leads to higher total adoption. Our findings suggest that the presence of artificial agents in social networks can alter diffusion.

cs.SI · econ.GN · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15404

Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Shuibai Zhang, Junhyuck Kim, Gyeongman Kim, Jaewoong Cho

原文摘要

Reinforcement learning (RL) has become central to post-training large language models (LLMs). However, popular RL methods like GRPO incur non-negligible overhead by computing both old-policy and current-policy likelihoods to form importance sampling ratios. In this work, we propose Likelihood-Gated Policy Optimization (LGPO), which enforces a soft trust region constraint via likelihood-based gating, eliminating the need to compute old-policy likelihoods. Empirically, we show that removing the importance sampling correction term does not harm training stability, whereas removing the trust region mechanism can lead to collapse. Moreover, ratio-based clipping can fail in fully on-policy training: the importance ratio stays at 1, so the ratio-based trust region constraint never activates. Under standard training settings where GRPO is stable, LGPO achieves comparable training stability and peak performance while reducing training time by ~18% on average relative to a standard implementation that recomputes old-policy likelihoods. In fully on-policy training, where GRPO fails, LGPO remains stable, enabling more efficient and robust LLM RL post-training across training regimes.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15372

LLMRunner: Closed Workload Model Performance Testing Framework for LLM Servings

Arush Upadhyaya, Debadatta Mishra

原文摘要

Performance testing large language model (LLM) serving engines is a crucial requirement considering the criticality of the infrastructure for deploying conversational AI at scale. Most of the benchmarking tools used to carryout performance evaluation of LLM serving do not capture realistic workload orchestration unlike closed workload performance testing infrastructure used in other domains such as web and database engines. For example, state-of-the-art LLM benchmarks for performance testing model traffic as streams of independent single-turn and stand-alone requests omitting the end-user behavior such as think-time between conversational turns. We present LLMRunner, a performance tester for LLM serving that addresses this gap by providing a framework to generate realistic load consisting of multi-turn conversations with configurable end-user parameters such as number of users in the workload loop, think-time distributions etc. Moreover, LLMRunner provides declarative matrix-sweep experiment plans, integrated GPU and KV-cache monitoring, and an automated artifact collection and plotting subsystem. We use LLMRunner to comparatively analyze the performance of LLM serving when NVIDIA CUDA Unified Virtual Memory (UVM) is used as a drop-in replacement memory allocator for the Key-Value cache (KV-Cache). Our test demonstrates that UVM incurs no measurable throughput or latency penalty compared to the baseline memory allocation technique for non-oversubscription scenarios.

cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15342

MechBench: A Domain-Specific LLM Benchmark for Parallel Mechanisms

Zhihao Xia, Tingting Wang, Hui Li, Yongheng Xing, Chunxu Tian

原文摘要

Parallel mechanisms pose distinctive challenges to large language models (LLMs), as valid reasoning depends jointly on mechanism topology, loop closure, geometry, joint types, and modeling assumptions. Yet existing LLM benchmarks provide little systematic coverage of such domain-specific knowledge, constraint-sensitive analysis, and constructive design. To fill this gap, we introduce MECHBENCH, a 2,541-question benchmark for evaluating LLMs in parallel mechanisms across professional knowledge, mechanism analysis, and design. MECHBENCH contains standard and challenge tiers spanning six capability categories and nine executable analysis and design tasks. It is constructed through MECHFORGE, a domain-grounded framework that combines expert-organized knowledge, LLM-assisted question generation, programmatic instance generation, two-stage expert review, and task-aware scoring with exact matching, rubric-based evaluation, and program verification. We further develop MECHGPT as a diagnostic domain-adapted model. Experiments show that strong knowledge performance does not directly translate into executable mechanism reasoning: leading closed-service models achieve over 95 on the standard tier but only 47-60 on the challenge tier, while domain adaptation substantially improves MechGPT over its Qwen3-8B baselines but leaves a large gap in constrained analysis and design. These results establish MECHBENCH as a systematic testbed for measuring domain-specific LLM capabilities in mechanism science.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.02719

Large Language Model-Driven Context-Aware Eco-Feedback Generation and Evaluation

Wooyoung Jung, Prosper Babon-Ayeng

原文摘要

The objective of this study is to demonstrate the potential of generating context-aware eco-feedback - eco-feedback that reflects a household's contextual characteristics alongside its energy use patterns - through a large language model-integrated framework. Previous studies have introduced personalized eco-feedback, mostly relying on household energy use patterns; however, they frequently did not reflect distinct household characteristics, including their persona or non-negotiable routines, leaving eco-feedback ineffective and sometimes superficial. To address these limitations, we introduce a contextual engineering framework that generates eco-feedback using a self-consistency with chain-of-thought prompt, leveraging household energy analysis data, utility rate structures, and household characteristic information. We conducted a rigorous empirical validation and a combinatorial evaluation analysis to assess this framework systematically. The former tested the framework's ability to generate accurate and contextually grounded eco-feedback for three households by comparing its output against reference interventions independently derived from the same household data. The latter examined the framework's adaptability across 400 scenarios spanning 50 households, two utility rate structures, and four behavioral personas. Our framework generated eco-feedback that aligned with reference interventions at a mean rate of 92.0% and grounded its recommendations in the provided household data with 95.7% citation accuracy. It also proved highly adaptive, shifting both the appliances targeted and the energy-saving strategies recommended in response to rate structure and household context. Ultimately, this study contributes to realizing the next level of context-aware interactions between occupants and buildings which paves the way for higher occupant living quality and sustainability.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15325

CaseScope: A Multi-Field Benchmark for Case-Level Pathology Diagnosis with Multimodal LLMs

Wenchuan Zhang, Chengyang Zhang, Fengling Li, Ting Yin, Chen Shu, Jie Chen, Shuwan Zhang, Xiaoyan Wu 等 12 位作者

原文摘要

Pathologists rarely diagnose from a single image: they scan a section at low power for architecture, zoom into selected fields for cytology, and integrate the evidence across views and scales. Pathology benchmarks for multimodal large language models (MLLMs), however, mostly ask about one image or require whole-slide pipelines, and the few that show several fields draw nested regions from cancer slides of one public cohort. We introduce CaseScope, a benchmark of diagnosis from several curated fields of one lesion: CaseScope-Teaching, 436 cases from a residency-training image library, reconstructed, de-identified, harmonised against a WHO-based ontology and re-examined by a pathologist wherever an automated pre-review raised a doubt, and CaseScope-Atlas, 800 cases from 88 published atlases (387 of them figure series of one disease), labelled from the captions by two LLMs that must agree. They cover 843 entities across 18 organ systems and pose 4,679 items in six tasks, from open-ended and ten-way diagnosis with ontology-guided hard negatives under circular evaluation to the verification and location of morphological findings. Across twenty-eight open and four proprietary MLLMs, diagnoses are unstable -- the best open and proprietary models are correct under all ten option rotations on 17.9% and 61.7% of the teaching cases -- and wrong answers favour the classic look-alike; open models make little use of the additional fields on teaching cases, where the one-line specimen site matters more, although on atlas cases with three or more fields the fields count about as much as the site; and most open models verify findings barely above chance (median 62.0% vs. 50%, best 81.5%), gaining a median +3.4 points from images; proprietary models reach 83.2-93.2%. Rankings broadly replicate between the sources. The evaluation code is available at https://github.com/Wenchuan-Zhang/CaseScope.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15317

BiPOP: Partial-Order Planning for Long-Horizon Bimanual Robotic Manipulation

Kun Chu, Xufeng Zhao, Jan-Gerrit Habekost, Cornelius Weber, Stefan Wermter

原文摘要

Bimanual robotic manipulation is versatile, yet its central challenge lies not only in executing dexterous motion with each hand, but also in coordinating the two arms for long-horizon manipulation under coupled spatial and temporal constraints. Prior work has largely focused on endowing robots with human-level manipulation skills, paying less attention to the structure of bimanual behaviour itself: many practical tasks are a coordinated composition of reusable unimanual skills and a small set of synchronous bimanual skills. This makes high-level spatio-temporal coordination, rather than skill acquisition alone, a key bottleneck for efficient bimanual execution. We propose BiPOP, a framework that couples Large Language Models (LLMs) with Temporal Partial-Order Planning for long-horizon bimanual manipulation. At its core is an explicit spatio-temporal model that partitions the workspace by arm reachability and captures inter-arm dependencies, arm assignment, synchronization requirements, and opportunities for safe concurrent execution. Building on this model, an LLM translates natural-language instructions into a formal PDDL specification, while a temporal planner enforces the constraints and schedules actions, yielding plans that are logically consistent at the symbolic level and efficient through parallel execution. On simulated long-horizon tasks of varying complexity, BiPOP outperforms open-loop planning with strong reasoning models and closed-loop ReAct-style planning in success rate, planning time, and plan efficiency, and the full pipeline runs end to end on the real bimanual robot NICOL. A failure analysis further shows that LLM-only planners mainly violate spatial and temporal coordination constraints, which motivates delegating these constraints to a symbolic planner. Code: https://github.com/Kchu/BiPOP

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12305

HumanSightBench: A Benchmark for Human Visual Perception in MLLMs

Zixin Su, Yangguang Lin, Zegang Peng, Yuntong Sun, Xuanyi Wang, Jiahao Wang, Qiankai Xu, Bing Yuan 等 13 位作者

原文摘要

Multimodal large language models (MLLMs) have demonstrated strong performance on knowledge-intensive and reasoning-based vision-language benchmark datasets, but still struggle to solve the visual questions that people can solve easily. Evaluating the differences between MLLMs and human-level visual perception is challenging due to end-to-end evaluation which combines various skills, or because we are uncertain if individual items are valid. Specifically, observed errors may reflect visual perception, language priors, background knowledge, question ambiguity, and underspecified answers. Our guideline for HumanSightBench is that we construct items that are human-easy by construction and model-hard by evaluation. HumanSightBench contains 2,876 visual questions with short answers across 7 top-level perceptual categories and 21 subcategories. We only include items that pass five inclusion gates: question clarity, answer uniqueness, visual grounding, human solvability, and text-only shortcut filtering. According to the protocol, errors are defined as incorrect answers on human-validated visual tasks with the evaluated interface. The inclusion gates are intended to reduce confounds from ambiguity and external knowledge. The best pass@3 score is 65.6% across eight evaluated MLLMs. No evaluated model exceeds 27.5% on Counting. These results identify capability gaps that are hidden by overall scores and can help future training experiments and held-out evaluation.

cs.CV · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.19363

LongReasonArena: A Long Reasoning Benchmark for Large Language Models

Jiayu Ding, Shuming Ma, Lei Cui, Nanning Zheng, Furu Wei

原文摘要

Existing long-context benchmarks for Large Language Models (LLMs) focus on evaluating comprehension of long inputs, while overlooking the evaluation of long reasoning abilities. To address this gap, we introduce LongReasonArena, a benchmark specifically designed to assess the long reasoning capabilities of LLMs. Our tasks require models to solve problems by executing multi-step algorithms that reflect key aspects of long reasoning, such as retrieval and backtracking. By controlling the inputs, the required reasoning length can be arbitrarily scaled, reaching up to 1 million tokens of reasoning for the most challenging tasks. Extensive evaluation results demonstrate that LongReasonArena presents a significant challenge for both open-source and proprietary LLMs. For instance, even GPT-5 achieves only 27.8% accuracy on Level 3. Further analysis also reveals that the accuracy exhibits a linear decline with respect to the logarithm of the expected number of reasoning steps. Our code and data are available at https://github.com/LongReasonArena/LongReasonArena.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15250

Multi-head Quantum Neural Networks: Replacing Transformer Blocks with NISQ Modules inside a 30-Billion-Parameter LLM

Maforikan Amoussou, Borja Aizpurua, Sukhbinder Singh, Román Orús, Hans-Arno Jacobsen

原文摘要

We introduce the multi-head quantum neural network (QNN), a quantum module compatible with noisy intermediate-scale quantum (NISQ) devices that can replace transformer blocks inside pre-trained large language models (LLMs) with little loss in accuracy and with far fewer parameters than the blocks it replaces. Encoding a model's $D$ hidden neurons into a qubit register is the obstacle: amplitude encoding scales poorly in circuit depth and angle encoding in qubit count, so neither is practical at production-scale width. We instead partition the hidden space into $k$ disjoint heads, angle-encode each into an $n_q$-qubit register, process the heads in parallel, and couple them through constrained classical linear layers, the mixers. Performing surgery on Qwen3-30B-A3B-Instruct-2507, we show that a single multi-head QNN with $145\,281$ trainable parameters ($D=2048$, $k=32$, $n_q=8$, $L=4$) can replace a contiguous span of eight transformer blocks, displacing $16.33\%$ of the model's parameters. Ablations show that, for a single replaced block, the quantum heads (circuits followed by a learned readout), and not the classical mixers alone, recover the displaced function, whereas for fused spans the mixers alone come within $1$-$3\%$ of the full module in perplexity. Whether this benefit is specific to trained, entangling quantum circuits is not established: controls that switch the entangler off (two seeds), or freeze the circuit at its initial or at uniformly random angles (one seed), beat the full module on held-out perplexity, and a parameter-matched classical multilayer perceptron remains a few percent ahead of the full module. We train classically with exact statevector simulation, then execute the quantum heads of our fusion checkpoints on a $156$-qubit IBM Heron processor, showing that NISQ-scale quantum modules can be installed in a production-scale LLM and run on hardware.

quant-ph · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13651

DrugCoding: A Scientific Programming Agent for Drug Discovery

Junwei Hu, Zhuohao Lin, Kun Li, Hengnan Zhang

原文摘要

Drug discovery involves multiple interconnected research stages, including molecular design, property prediction, and virtual screening. These processes are characterized by complex workflows, interdependent computational tasks, and diverse specialized tools, placing substantial demands on the coordination of scientific models and computational resources. However, existing large language model (LLM)-based scientific agents still face challenges in autonomous planning of complex tasks, adaptive selection of specialized models, and reliable execution of multi-stage scientific computations, limiting their effectiveness in automating complex drug discovery workflows. To address these challenges, we propose DrugCoding, a scientific programming agent system that integrates scientific task planning, adaptive model routing, multi-agent collaboration, and programmatic tool execution. DrugCoding enables autonomous task planning and dynamic model adaptation for complex research objectives. It can flexibly invoke specialized scientific models, autonomously generate and execute code according to task requirements, and leverage multi-agent collaboration to support efficient execution and reliable validation of complex scientific tasks. To evaluate DrugCoding's performance in scientific tool invocation and multi-stage task execution, we conduct multi-turn tool-calling experiments across diverse language models and scientific tool interfaces. Experimental results demonstrate that DrugCoding achieves an average session-level Pass@1 of 97.35% on the full benchmark, outperforming the strongest baseline, Codex, by 9.24%. On the challenging subset, DrugCoding achieves 97.92%, exceeding the strongest baseline.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15231

TQIR: Trellis Quantization with Integer Reconstruction for Bandwidth-Efficient Edge LLM Acceleration

Kuang-Ting Huang, Tian-Sheuan Chang

原文摘要

Autoregressive large language model (LLM) inference is often limited by external-memory bandwidth, while existing ultra-low-bit trellis quantization reconstructs floating-point weights and leaves runtime Hadamard-transform and decoder costs unresolved. This paper presents TQIR, an algorithm--hardware co-design that decouples storage precision ($S$) from decoded-weight ($W$) and activation ($A$) compute precisions, enabling a better accuracy--hardware trade-off. TQIR performs trellis matching with floating-point candidates offline while constraining each candidate to an INT8 or INT4 codeword that can be reproduced exactly for integer GEMM at runtime. To reduce transform cost while preserving the integer weight path, TQIR relocates the reverse Hadamard transform to the activation side and employs an $H_{128}$ Subspace Hadamard Transform, together with a subspace-aligned $128\times2$ trellis tile that preserves the original 256-weight sequence length. The configurable decoder, synthesized in a TSMC 16-nm process, delivers 307.2~Gweights/s in 0.0509~mm$^2$ and achieves 13.93$\times$ and 1.52$\times$ the normalized decoder-area efficiency of Ecco and Codeword Decomposition, respectively. These results show that fixed-rate trellis compression can reduce weight traffic while sustaining an integer-GEMM datapath matched to the evaluated memory and PE rates.

cs.AR

查看论文
arXiv ↗PDF ↗