跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.14242 · v1

PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles

PARLEY:通过合作式非对称谜题评估大语言模型协作

首次提交 2026-11-10 23:54
版本更新 2026-11-10 23:54
雷达观测 2026-11-11 13:07
arXiv ↗PDF ↗

摘要

As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint coordination, perspective-taking, and spatial reasoning). GPT-4o agent pairs succeeded in 60.5% of conversations (N=400, 100 per task), with task-level variation (34-80%) reflecting distinct collaborative demands. From these conversations, we derived the data-driven PAC taxonomy: six failure types organized into Perception (visual interpretation and spatial reasoning), Adaptation (progress tracking and feedback integration), and Coordination (verification and grounding). Failure to incorporate external feedback was a critical indicator of unsuccessful collaboration, with agents repeatedly applying unsuccessful strategies. We also show that a taxonomy-guided intervention (N=200) improved average task success to 70.5%. These results demonstrate how PARLEY can be used to derive meaningful, data-driven insights that can in turn lead to improved agentic collaboration.

作者备注:12 pages, 8 figures, 2 tables

AI 论文解读

基于摘要 · 非全文审阅

作者提出 PARLEY 平台,用四类认知心理学启发的非对称谜题任务研究 LLM 智能体协作,并据此归纳失败类型、尝试分类引导的干预。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-10 23:54 · 最新观测版本

PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles

As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint coordination, perspective-taking, and spatial reasoning). GPT-4o agent pairs succeeded in 60.5% of conversations (N=400, 100 per task), with task-level variation (34-80%) reflecting distinct collaborative demands. From these conversations, we derived the data-driven PAC taxonomy: six failure types organized into Perception (visual interpretation and spatial reasoning), Adaptation (progress tracking and feedback integration), and Coordination (verification and grounding). Failure to incorporate external feedback was a critical indicator of unsuccessful collaboration, with agents repeatedly applying unsuccessful strategies. We also show that a taxonomy-guided intervention (N=200) improved average task success to 70.5%. These results demonstrate how PARLEY can be used to derive meaningful, data-driven insights that can in turn lead to improved agentic collaboration.

查看此版本解读 →查看此版本原文 ↗