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

+1030新增论文
+790其中 AI 相关
+128已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 02:50 · 全站最近入库：2026-11-11 22:47各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 03:06 — 2026-11-12 03:06（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：2026-11-12 02:50最近发现新增版本：2026-11-11 22:47库内论文最新更新时间：2026-11-11 08:00

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。

21,673 已收录论文18,321 AI 相关6,056 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 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 02:48（北京时间）
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.814ACL Anthology · ACL 2026

LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning

Wenxiang Zheng Harbin Institute of Technology, Guo Tang, Shixin Jiang, Liangyu Huo, Xiyuan Zhang Du Xiaoman Technology (Beijing) Co., Ltd., Jian Xie Beijing Baichuan Intelligent Technology Co., Ltd., Ming Liu Harbin Institute of Technology

原文摘要

Retrieval-Augmented Generation (RAG) is widely used to ground large language models (LLMs) in external knowledge and improve factual accuracy. Prior work has explored iterative and self-reflective mechanisms to refine reasoning, but these approaches rely on internal model judgment and lack formally grounded, verifiable feedback. As a result, RAG systems may still produce logically inconsistent or contradictory answers in multi-step reasoning. In this paper, we propose LCR-RAG, a framework that integrates neuro-symbolic verification with reinforcement learning to explicitly optimize logical consistency. The core of our approach is a Logic-Consistency-driven Reward (LCR), which converts discrete logical signals—such as contradictions or incomplete inference chains—into a structured reward signal. This reward guides a PPO-based agent to iteratively rewrite queries and correct reasoning errors. Experiments on HotpotQA, ASQA, and TriviaQA show that LCR-RAG consistently outperforms strong RAG baselines, with ablation results indicating that the LCR mechanism is the primary source of improvement, even under noisy or conflicting retrieval conditions.

cs.CL

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