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

+549新增论文
+443其中 AI 相关
+62已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 17:33 — 2026-11-21 17:33(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19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。

29,158 已收录论文24,181 AI 相关8,992 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 9 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.24578

BaseRSI: Recursive Self-Improvement of a Base Vision-Language Model via Training-Free Harness Internalization

Mingda Zhang, Yuanhao Dong, Qiang Huang, Rui Qian, Yanjin Li, Zhenyu Liu, Xiao Huang, Zihao Yang 等 11 位作者

原文摘要

Recursive self-improvement (RSI) is moving from the harness of prompts and tools around a base model toward the model itself. However, existing RSI still faces key challenges, including harness-bound gains that stay outside the base model, black-box supervision that reads only the model's outputs, and imprecise edits whose site and strength are fixed in advance. To address these challenges, we propose BaseRSI, a new paradigm of Recursive Harness Internalization: the base model improves its harness, then writes what the harness adds into its own weights through training-free edits, round after round on its own responses. To support this paradigm, we introduce ReGap, a mechanism that supervises every transformer block with the high-dimensional activation difference that the harness makes at that block alone, and updates the block's weights along this signal in a low-dimensional subspace. Building on this mechanism, we further propose ReKey, an algorithm that writes this signal by regression into a few key-value neurons of every block, and measures the site and strength of each edit on the model's own responses. Moreover, the base model fills every role of this recursion with forward passes alone, and its edits, written at different sites, compose in one checkpoint without refitting. Experimental results on ten visual reasoning benchmarks show that BaseRSI consistently improves a base vision-language model both in distribution and on held-out benchmarks. Our code is available at https://github.com/beita6969/BaseRSI.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.04950

How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation

Xiaoyu Ma, Haoyue Liu, Zhichao Wang, Jionghao Zhu, Xiaoying Tang

原文摘要

On-policy distillation (OPD) improves the reasoning capabilities of small language models through token-level teacher supervision on student-generated trajectories. Yet can teachers that excel at solving problems independently also guide student reasoning effectively? Prior work shows that when student prefixes follow reasoning paths that differ from the teacher's own or contain errors, teachers can be less accurate when continuing from these prefixes than when solving problems independently. To this end, we propose Prep-OPD, which uses reinforcement learning (RL) before distillation to train the teacher to adapt to the student's existing reasoning state and correct course when errors arise. Training optimizes teacher continuations from fixed student prefixes using final-answer correctness as the reward. The prepared teacher then trains the student through trajectory guidance and token-level supervision. We evaluate Prep-OPD on eight mathematical reasoning benchmarks, using Qwen3-4B-Instruct-2507 as the teacher and Qwen3-0.6B and Qwen3-1.7B as students. With the 4B teacher and 1.7B student, Prep-OPD improves average accuracy over standard OPD and the strongest baseline, Relay-OPD, by 8.28 and 2.30 percentage points, respectively. Controlled experiments further show that teacher RL conditioned on student-generated prefixes yields higher student accuracy than problem-start teacher RL with and without handoff on Qwen3-1.7B. Reusing the same prepared teacher also improves Qwen3-0.6B.

cs.LG

版本更新 · v3arXiv:2508.08772

Certified Boost Design for Quality-Aware Auto-Bidding

Huanyu Yan, Yu Huo, Min Lu, Weitong Ou, Xingyan Shi, Ruihe Shi, Xiaoying Tang

原文摘要

Online advertising platforms balance advertiser value, publisher-assessed ad quality, and platform revenue. However, boost design in this three-stakeholder architecture remains insufficiently studied. In this paper, we develop certified boost mechanisms under a payment rule that deducts boosts from winners' payments. We establish a capped benchmark-competitive condition that guarantees a quality-aware liquid-welfare lower bound parameterized by the certificate strength, boost cap, and bid cap, with an explicit penalty for an insufficient boost cap. We then derive a closed-form canonical boost. For the observed state, it matches the welfare-optimal benchmark allocation whenever its certificate margin seats every benchmark winner, and among all certified boosts that do so it maximizes the platform's retained revenue. On AuctionNet, a public benchmark built on Alibaba's real-world production advertising environment, we evaluate canonical across ten bidding policies on multiple episodes. Under a twofold shock to the strongest rival's bid, canonical achieves $97.6\%$ mean welfare efficiency, compared with $91.1\%$ for the strongest baselines. Controlled stress tests link this protection to the certificate margin, while a ten-policy cap sweep shows diminishing welfare gains as retained revenue falls.

cs.GT

版本更新 · v2arXiv:2605.06978

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

Kun Zeng, Yu Huo, Siyu Zhang, Haoyue Liu, Yuecheng Zhuo, Zi Ye, Yuquan Lu, Junhao Wen 等 9 位作者

原文摘要

Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Across SkillsBench, ALFWorld, and Terminal-Bench 2 with six backbones, GoSkills attains the highest mean reward or accuracy among the evaluated methods in every benchmark-backbone setting, and matched controls show higher reward and fewer agent turns with group selection than with fixed-contract or post-hoc role-annotation alternatives.

cs.CL · cs.AI

新论文 · v1arXiv:2611.05917

DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion

Yanjin Li, Bingbing Qiu, Qiang Huang, Rui Qian, Yanfeng Li, Jian Wang, Xiaoying Tang, Mingda Zhang

原文摘要

Sparse attention accelerates few-step video diffusion transformers by computing a few key blocks exactly and compensating for the rest. However, existing sparse attention still faces key challenges, including identification overhead from finding critical blocks at every denoising step, suboptimal budget allocation that sets sparsity budgets uniformly or by local metrics, and cross-step error accumulation as reused masks or clusters go stale. Observing that the errors left on skipped blocks cancel each other once every key is compensated, we propose DecoupAttn, a new paradigm of decoupled sparse attention: semantic clusters compensate every key, and exact attention corrects their error on a few blocks fixed once offline by position. To support this paradigm, we introduce Distortion Budget, a rate-distortion objective for budget allocation that places exact computation across timesteps, layers, and heads where it removes the most distortion that compensation leaves in the final latent. Built on this budget, we further propose Reassign Cache, in which each step reassigns the drifting keys to cached centroids and refreshes compensation while the budgeted blocks stay fixed. Moreover, DecoupAttn is training-free: a few calibration clips compile one plan offline, and inference runs standard block-sparse kernels with one fused compensation kernel. Our code will be released after submission.

cs.CV

新论文 · v1arXiv:2610.34759

From Belief Inference to Task Action: A Multi-Level Evaluation of Theory of Mind on Verifiable Tasks

Zhenshuai Yin, Yongxin Guo, Mingda Zhang, Zhongze Luo, Haoyue Liu, Lianmin Zhang, Xiaoying Tang

原文摘要

Effective collaboration requires language models to understand what others know and believe, and to act accordingly. Models that assume others share their information may omit necessary communication and undermine coordination. Many theory-of-mind (ToM) benchmarks assess mental-state inference through story questions, but correct answers do not establish that models can use these judgments in subsequent tasks. We introduce a multi-level evaluation built on existing, verifiable tasks. We extend household collaboration and calendar scheduling with asymmetric information while retaining their original constraints and validators. Independent interfaces assess world understanding, information access, beliefs, decisions, and execution. Controls supply personal evidence or correct beliefs to distinguish state recovery from state use. Across six model configurations, these abilities diverge. On matched scheduling cases, Claude recovers all agent beliefs correctly but produces subjectively optimal plans in only 67.9% of cases. In household collaboration, supplying beliefs raises Qwen-27B success from 55.0% to 75.0%, yet Qwen-4B answers every fixed supplied-belief source question correctly while completing only 20.0% of the corresponding continuation condition. These results show why ToM evaluation must connect perspective inference to independently verified decisions and task consequences.

cs.CL

新论文 · v1arXiv:2610.34737

LADDER: Diagnosing Domain-Level Self-Assessment Under Noisy Feedback

Zhenshuai Yin, Jianshu Liang, Xuyue Xiong, Yongxin Guo, Mingda Zhang, Zhongze Luo, Haoyue Liu, Lianmin Zhang 等 9 位作者

原文摘要

Knowing when they are reliable is essential for language models to support human-AI collaboration. Yet interaction feedback is not always complete or correct, and may mislead models' understanding of their own capabilities. We introduce LADDER to study how language models assess themselves under unreliable feedback. Our findings show that models can accurately report supplied performance information while still struggling to form trustworthy self-assessments from interaction experience. Apparently accurate assessments can obscure capability differences and do not necessarily predict future task performance. These findings suggest that trustworthy self-assessment should be evaluated against observed task performance and its predictive value. Our study provides empirical evidence of the limits of model self-knowledge and a basis for evaluating capability awareness in reliable human-AI collaboration.

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.206ACL Anthology · ACL 2026

G^2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance

Yongxin Guo ByteDance Inc., Wenbo Deng, Zhenglin Cheng Westlake University, Xiaoying Tang The Chinese University of Hong Kong, Shenzhen

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest improvements for small-size language models (SLMs). To address this limitation, we investigate Guided GRPO, which injects ground-truth reasoning steps into roll-out trajectories to compensate for SLMs’ inherent weaknesses. Through a comprehensive study of various guidance configurations, we find that naively adding guidance delivers limited gains. These insights motivate G^2RPO-A, an adaptive algorithm that automatically adjusts guidance strength in response to the model’s evolving training dynamics. Experiments on mathematical reasoning and code-generation benchmarks confirm that G^2RPO-A substantially outperforms vanilla GRPO. Our code and models at available at https://github.com/T-Lab-CUHKSZ/G2RPO-A.

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.537ACL Anthology · ACL 2026

Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs

Haoyue Liu, Zhichao Wang, Yongxin Guo ByteDance Inc., Haoran Shou, Xiaoying Tang The Chinese University of Hong Kong, Shenzhen

原文摘要

Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adaptive Prompt Structure Factorization (aPSF), an API-only framework (prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific prompt structures as semantic factors. aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor’s marginal contribution via validation-performance changes, and error-guided factor selection routes updates to the current dominant failure source for more sample-efficient optimization. Across multiple advanced reasoning benchmarks, aPSF outperforms strong baselines, improving accuracy by up to +4.29 percentage points on average, and reduces optimization cost by 45–87% tokens on MultiArith while reaching peak validation in 1 step.

cs.CL

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