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

+1284新增论文
+1011其中 AI 相关
+150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 10:50各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 12:35 — 2026-11-20 12:35(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 10:50库内论文最新更新时间:2026-11-19 12:39

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。

28,155 已收录论文23,386 AI 相关8,624 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 4 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)
新论文 · v1arXiv:2611.24590

Think Offline, Act in Real Time: Self-Improving Visual Game Agents through Code

Zipeng Qiu, Shusheng Xu, Jiale Li, Yukun Zhou, Chenyue Li, Wenshuang Li, Tongkai Yang, Binhang Yuan

原文摘要

Pre-trained models can read screens and reason about games, yet on an unfamiliar game, an agent still has to learn to play. We ask how an agent can self-improve on such a game from a few of its own attempts, in real-time visual games where the agent sees only the screen and the game keeps running while the agent thinks. We study two kinds of policy that can carry this improvement. In model as policy, a model selects actions during play; we adapt real-time chunking so that committed actions keep executing while the model reasons, and train a 2B controller for this interface. In code as policy, a model writes, tests, and revises a program between attempts, and the program acts during play. Across 170 GameWorld tasks, with at most eight one-minute executions per run, code as policy reaches 47.80% mean progress, against 30.90% for our trained controller, and leads in all five game categories. Improving the controller's weights on a single game, by contrast, yields only modest gains. These results favor letting a model think offline and storing what it learns in a program that acts in real time. Project repository: https://github.com/TabibitoQZP/SIGame

cs.AI

新论文 · v1arXiv:2611.21710

Learning In-Context Adaptivity for LLMs through Continual Gameplay

Jiale Liu, Zun Li, John Schultz

原文摘要

LLM agents are increasingly deployed in long-horizon tasks where they must explore, gather experience, and adapt their decisions accordingly. We name this capability in-context adaptivity: improving decisions across episodes from experience accumulated in context. We propose to evaluate it in repeated imperfect-information games against unknown opponents. In these games, fixed game-theoretically optimal policies cannot achieve maximum reward, whereas adapting to the opponent increases returns across games. We design a paired protocol that evaluates each agent with and without memory under identical conditions to isolate experience gain from single-game skill. Evaluation shows that memory brings little performance gain for open-weight models and inconsistent gains for frontier models. Our analysis of the agents' summaries and actions identifies a memory-doing gap in which models accurately record opponent tendencies yet rarely depart from default play. To close this gap, we construct a pool of exploitable opponents and post-train Qwen3.5-9B with supervised fine-tuning followed by trajectory-level reinforcement learning. We optimize full-match return across context segments so summary generation and action selection are trained together. On unseen opponents, our 9B RL policy doubles experience gain over supervised fine-tuning in Leduc Hold'em and increases it fivefold in No-Limit Hold'em. Across 35 opponents, our policy matches or surpasses frontier models, generalizes beyond its training horizon, and retains most of its gain on summaries from frontier models.

cs.GT

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1382ACL Anthology · ACL 2026

One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models

Shunwen Bai Zhejiang University, Jiahuan Zhang, Haoran Huang, Yurun Wang, Jiale Liu, Yanxi Wu Zhejiang University, Ningzhe Yu, Yudong Gao Hong Kong University of Science and Technology 等 9 位作者

原文摘要

Currently, large language models (LLMs) have significant limitations in spatial reasoning, particularly in the absence of visual input. To address this issue, we introduce SODA (Spatial OODA), which draws inspiration from the OODA cognitive loop (Observe, Orient, Decide, Act), originally designed to enhance human decision-making in dynamic environments. Specifically, we embed the OODA loop into multiple control tasks, generating the SPOD-143k dataset, and successfully integrate it into LLMs through a two-phase and spatia-aware training strategy (SFT and GRPO). Furthermore, to fill the gap in evaluating spatial reasoning in purely text-based LLMs, we introduce the SPOD-Bench benchmark, including multiple tasks divided into three levels of difficulty. Experimental results show that SODA significantly enhances the spatial reasoning capabilities of LLMs across testing scenarios including SPOD-Bench, SPACE and applications, providing a replicable and effective paradigm for improving the spatial cognition of LLMs.

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.657ACL Anthology · ACL 2026

TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems

Jiale Liu Pennsylvania State University, Victor Bursztyn Adobe Systems, Lin Ai, Haoliang Wang Adobe Research, Sunav Choudhary Adobe Research, Saayan Mitra Adobe Research, Qingyun Wu

原文摘要

In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this setting, as they tend to suppress minority perspectives rather than resolve underlying disagreements. We present TeamFusion, a multi-agent system designed to support teamwork in open-ended domains by: 1. Instantiating a proxy agent for each team member conditioned on their expressed preferences; 2. Conducting a structured discussion to elicit agreements and disagreements; and 3. Synthesizing more consensus-oriented deliverables that feed into new iterations of discussion and synthesis. We evaluate TeamFusion on two teamwork tasks where team members can judge how well their individual views are represented in team decisions and how consensually good the final deliverables are, finding that it outperforms direct aggregation baselines across metrics, tasks, and team configurations.

cs.CL · cs.MA

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