cs.MANov 10, 2026

PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles

Authors: Javier Hernandez, Andrew D. Wilson

Organizations: Microsoft Research, Cambridge, MA, USA · Microsoft Research, Redmond, WA, USA

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry

    Oct 29, 2025Run Peng, Ziqiao Ma, Amy Pang +5Multi-Agent LLM SystemsLLM Agent Verification

  2. More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration

    Apr 9, 2026Advait Yadav, Sid Black, Oliver SourbutMulti-Agent CoordinationMulti-Agent Collaboration