跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1199新增论文
+950其中 AI 相关
+132已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 16:53各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 18:44 — 2026-11-20 18:44(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:2026-11-20 08:48最近发现新增版本:2026-11-20 16:53库内论文最新更新时间:2026-11-20 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。

28,609 已收录论文23,738 AI 相关8,785 有修订112 HF 社区发现

浏览论文库

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 10 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v3arXiv:2610.26825

MemT-1.0: Towards Memory-Native Evolution

Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Yu Yu 等 74 位作者

原文摘要

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano, MemT-1.0-Flash, and MemT-1.0-Pro, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.

cs.CL · cs.LG

版本更新 · v2arXiv:2606.28725

DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation

Yuting Xin, Hanyu Cai, Binqi Shen, Lier Jin, Lan Hu

原文摘要

Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, and strategic adaptation to enforcement. Existing drift detection methods often focus on global distributional change, but such signals may miss safety-relevant shifts that emerge in localized harm subspaces or high-risk model-error regions. This paper introduces DriftGuard, a safety-aware adaptive moderation framework that combines multi-monitor drift detection with selective model updating. The framework tracks global text drift, identity-harm drift, model uncertainty, toxic-risk drift, and false-negative-risk drift. When safety-relevant change is detected, the model is updated using a hard-mix adaptation set that prioritizes likely false negatives, identity-related high-risk examples, false-positive-risk examples, and uncertain boundary cases. Experiments on Civil Comments temporal shift and Jigsaw-to-DynaHate cross-dataset shift show that safety-aware monitors detect risks missed by global drift alone. Hard-mix adaptation improves toxic recall and accuracy over no-update and random-balanced baselines. It raises toxic recall from 0.8453 to 0.8777 on Civil Comments and from 0.7107 to 0.8523 on DynaHate. Bootstrap analysis further shows stable DynaHate safety gains, with toxic recall increasing by 0.1418 and false-negative prevalence decreasing by 0.0781. Overall, DriftGuard links safety-aware drift detection with targeted, lightweight model updating for more robust adaptive toxicity moderation.

cs.CL

版本更新 · v2arXiv:2608.08942

Prompt Privilege in Large Language Models: Measuring and Mitigating Barriers to Equitable AI Access

Lier Jin, Lan Hu, Binqi Shen, Hanyu Cai, Yuting Xin

原文摘要

Large language models (LLMs) are increasingly used in healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of users' literacy, communication style, or prompt-engineering expertise. However, research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We call this accessibility challenge "Prompt Privilege": users with greater prompting expertise obtain better model performance despite expressing the same underlying intent. To address this problem, we propose the Prompt Equity Score (PES), a metric for evaluating performance consistency across user populations, and the Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent prompts while preserving their intent. PET shifts prompt optimization from users to AI systems, serving as an accessibility layer between users and foundation models. Experiments on MedQA reveal measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts. Applying PET reduces these differences, with no pairwise cohort differences reaching statistical significance in our evaluation. These results suggest that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for fairer, more trustworthy, and more inclusive AI systems.

cs.CL

新论文 · v1arXiv:2611.15359

MetaCom: Meta Codebook Learning for Robust V2X Semantic Communications

Muge Yu, Danlan Huang, Xinyi Zhou, Shuqi Chai, Zhiyong Feng

原文摘要

Collaborative perception in Vehicle-to-Everything (V2X) networks faces dual challenges: strictly limited bandwidth and channel impairments. Existing static quantization schemes often suffer from feature manifold drift caused by highly non-stationary traffic environments. To address this, we propose MetaCom, a robust digital semantic communication framework featuring a Meta-Codebook Learning paradigm. First, we introduce a Differentiable Quantized Semantic Communications (DQSemCom) module trained with perturbations induced by the simulated digital modulation and channel via Gumbel-Softmax relaxation. Building on this, we design a Bi-Level Meta-Evolution Mechanism (Bi-MEM) that treats manifold drift as a sequence of rapid adaptation tasks, aligning the codebook via data-level smoothing and parameter-level meta-updates. Furthermore, we validate MetaCom under AWGN, Rayleigh, and Rician fading channels. Experimental results demonstrate that MetaCom achieves superior trade-offs between perception precision and communication overhead, outperforming state-of-the-art methods by a significant margin under low-SNR conditions.

cs.IT

版本更新 · v4arXiv:2610.31303

The Value of Memory in Language Agents

Zehao Lin, Erenkai Zhu, Helan Hu, Xixuan Hao, Chunyu Li, Linyun Liu, Kai Chen, Chenxu Du 等 9 位作者

原文摘要

Language agents carry information from past experience into future tasks whose demands may be unknown or change over time. We develop a decision-theoretic account of the capability available in history, retained in storage and realized through use, together with the costs of recovery and revision. Drawing on comparison of statistical experiments, information acquisition and the value of computation, we express these values in units of avoided task loss. Recovery and revision define attainable risk-cost profiles and preservation across uses. A cost-aware simulation condition and five minimal counterexamples establish how information timing, access, computation, feedback and demand shape these comparisons; a pointer with zero answer mutual information can reduce the cost of exact recovery. Allocation and recovery criteria identify when gains pay for estimation, selection and evidence access. Complete-split studies on LoCoMo, LongMemEval-S and PersonaMem cover 3,075 questions and two readers. They show complementary value from saved state and recovered evidence, task-dependent performance orderings, and the role of reuse in amortizing construction costs. Multi-project workflows connect correction to preservation and validation costs. Together, the theory and studies support decisions about what to retain, which recovery options to preserve, and how to adapt memory as evidence and objectives evolve.

cs.AI · cs.CL

版本更新 · v2arXiv:2611.05877

When Does Better Confidence Improve a Knowledge-Graph Audit?

Zehao Lin, Kai Chen, Xixuan Hao, Erenkai Zhu, Chunyu Li, Helan Hu, Feiyu Xiong

原文摘要

Confidence estimates guide human review in LLM-built knowledge graphs, but an erroneous shared entity need not be the only reason an incident fact is wrong. We study how this distinction affects budgeted audits, alongside selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $Δ^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. An error-rate $\times$ fan-out baseline leaves 3.98-4.74 percentage points more errors than joint planning with the same actions. Independent-block planning also avoids this disadvantage: its held-out point estimates improve on a fact-only scalar baseline by 1.22-1.79 points and are slightly better than the joint model, although the frozen equivalence criterion remains inconclusive. On 300 DWIE training documents, independent and joint plans also outperform fan-out in point estimates, with extractor-dependent gains over fact-only review. For verification, a generic support check improves three of four model-budget configurations on each held-out set. These comparisons motivate evaluating complete-repair probabilities and retaining both fact-only and factorised baselines when choosing an audit model.

cs.CL

版本更新 · v4arXiv:2606.13657

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Guo Yu, Wenlin Liu, Yulan Hu, Hao-Xuan Ma, Jun-Peng Jiang, Han-Jia Ye

原文摘要

On-policy distillation (OPD) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student-generated trajectories and dense token-level teacher supervision. Yet how this hybrid training regime shapes a model remains poorly understood. We characterize the sparsity and geometry of OPD parameter updates across several language and vision-language model pairs and application settings. OPD updates are small and coordinate-sparse, while remaining distributed across layers and modules. This sparse support is operationally meaningful: masked training on the discovered subnetwork nearly recovers full-training performance. At the matrix level, the updates are numerically full-rank but spectrally concentrated. Their visible supports avoid coordinates emphasized by the source's principal structure and favor low-magnitude source coordinates, while the source singular-value spectra change little. Together, these findings show that OPD exhibits important weight-space signatures of on-policy post-training despite using dense teacher supervision.

cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1062ACL Anthology · ACL 2026

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling

Jiaxuan Wang, Yulan Hu Alibaba Group, Wenjin Yang Alibaba Group, Zheng Pan Alibaba Group, Xin Li Alibaba Group, Lan-Zhe Guo Nanjing University

原文摘要

In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and complex reasoning, the paradigm of reward modeling faces unprecedented challenges–most notably, the lack of benchmarks specifically designed to assess RM capabilities within tool-integrated environments. To address this gap, we present Plan-RewardBench, a trajectory-level preference benchmark designed to evaluate how well judges distinguish preferred versus distractor agent trajectories in complex tool-using scenarios. Plan-RewardBench covers four representative task families—(i) Safety Refusal, (ii) Tool-Irrelevance / Unavailability, (iii) Complex Planning, and (iv) Robust Error Recovery—comprising validated positive trajectories and confusable hard negatives constructed via multi-model natural rollouts, rule-based perturbations, and minimal-edit LLM perturbations. We benchmark representative RMs (generative, discriminative, and LLM-as-Judge) under a unified pairwise protocol, reporting accuracy trends across varying trajectory lengths and task categories. Furthermore, we provide diagnostic analyses of prevalent failure modes. Our results reveal that all three evaluator families face substantial challenges, with performance degrading sharply on long-horizon trajectories, underscoring the necessity for specialized training in agentic, trajectory-level reward modeling. Ultimately, Plan-RewardBench aims to serve as both a practical evaluation suite and a reusable blueprint for constructing agentic planning preference data.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1347ACL Anthology · ACL 2026

Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks

Xiang Cheng Renmin University of China, Yulan Hu Alibaba Group, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan Alibaba Group, Xin Li Alibaba Group, Yong Liu Renmin University of China

原文摘要

Travel planning is a natural real-world task to test large language models’ (LLMs) planning and tool-use abilities. Although prior work has studied LLM performance on travel planning, existing settings still differ from real-world needs, mainly due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries. To mitigate these gaps, we propose \mbox{\textbf{TravelBench}}, a benchmark for \textit{truly real-world} travel planning. We collect user queries, user preferences, and tools from real scenarios, and construct three subtasks—\textit{Single-Turn}, \textit{Multi-Turn}, and \textit{Unsolvable}—to evaluate agents’ three core capabilities in real settings: (1) solving problems independently, (2) interacting with users to elicit implicit preferences, and (3) recognizing the capability boundaries. To enable stable tool invocation and reproducible evaluation, we cache real tool-call results and build a sandbox environment which integrates ten travel-related tools, enabling agents to combine these tools to solve most practical travel planning problems. We evaluate multiple LLMs on TravelBench and find that even advanced models exhibit imbalanced performance across different capabilities. Our further systematic verification demonstrates the stability of the proposed benchmark. TravelBench provides a practical and reproducible benchmark to advance research on LLM agents for real-world travel planning.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.576ACL Anthology · ACL 2026

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning

Zhicong Li, Lingjie Jiang Peking University, Yulan Hu Alibaba Group, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen Southern University of Science and Technology, Zheng Pan Alibaba Group 等 10 位作者

原文摘要

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic models, which fail to adapt as the policy evolves. In on-policy RL, the agent’s trajectory distribution and error patterns shift over time, causing stationary critics to become stale and providing feedback of diminishing utility. To address this, we introduce ECHO (Evolving Critic for Hindsight-Guided Optimization), a framework that jointly optimizes the policy and critic through a synchronized co-evolutionary loop. ECHO utilizes a cascaded rollout mechanism where the critic generates multiple diagnoses for an initial trajectory, followed by policy refinement to enable group-structured advantage estimation. We address the challenge of learning plateaus via a saturation-aware gain shaping objective, which rewards the critic for inducing incremental improvements in high-performing trajectories. By employing synchronized dual-track GRPO updates, ECHO ensures the critic’s feedback stays synchronized with the evolving policy. Experimental results show that ECHO yields more stable training and higher long-horizon task success across open-world environments.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表