AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cadet, Xavier, Koh, Edward, Chin, Peter
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915651005710336
author Cadet, Xavier
Koh, Edward
Chin, Peter
author_facet Cadet, Xavier
Koh, Edward
Chin, Peter
contents Large Language Model (LLM) agents are increasingly studied in multi-turn, multi-agent scenarios, yet most existing setups emphasize open-ended role-play rather than controlled evaluation. We introduce AsymPuzl, a minimal but expressive two-agent puzzle environment designed to isolate communication under information asymmetry. Each agent observes complementary but incomplete views of a symbolic puzzle and must exchange messages to solve it cooperatively. Using a diverse set of current-generation and open-source LLMs, we show that (i) strong models such as GPT-5 and Claude-4.0 reliably converge across puzzle sizes on the solution by sharing complete information in two turns, (ii) weaker models often ignore partner messages or over-correct their hypotheses, and (iii) feedback design is non-trivial: simple self-feedback improves success rates, while detailed joint feedback can hurt performance. These findings show that even in simple cooperative tasks, LLM communication strategies diverge and depend on the granularity of feedback signals. AsymPuzl thus provides a testbed for probing the limits of multi-turn cooperation and opens avenues for studying coordination mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03466
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation
Cadet, Xavier
Koh, Edward
Chin, Peter
Multiagent Systems
Artificial Intelligence
Large Language Model (LLM) agents are increasingly studied in multi-turn, multi-agent scenarios, yet most existing setups emphasize open-ended role-play rather than controlled evaluation. We introduce AsymPuzl, a minimal but expressive two-agent puzzle environment designed to isolate communication under information asymmetry. Each agent observes complementary but incomplete views of a symbolic puzzle and must exchange messages to solve it cooperatively. Using a diverse set of current-generation and open-source LLMs, we show that (i) strong models such as GPT-5 and Claude-4.0 reliably converge across puzzle sizes on the solution by sharing complete information in two turns, (ii) weaker models often ignore partner messages or over-correct their hypotheses, and (iii) feedback design is non-trivial: simple self-feedback improves success rates, while detailed joint feedback can hurt performance. These findings show that even in simple cooperative tasks, LLM communication strategies diverge and depend on the granularity of feedback signals. AsymPuzl thus provides a testbed for probing the limits of multi-turn cooperation and opens avenues for studying coordination mechanisms.
title AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2512.03466