LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parsaee, Ali, Talebirad, Yashar, Szepesvári, Csongor, Ohal, Vishwajeet, Redman, Eden
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918249549004800
author Parsaee, Ali
Talebirad, Yashar
Szepesvári, Csongor
Ohal, Vishwajeet
Redman, Eden
author_facet Parsaee, Ali
Talebirad, Yashar
Szepesvári, Csongor
Ohal, Vishwajeet
Redman, Eden
contents Large Language Models (LLMs) are increasingly being utilized as autonomous agents, yet their ability to coordinate in distributed systems remains poorly understood. We introduce \textbf{LoopBench}, a benchmark to evaluate LLM reasoning in distributed symmetry breaking and meta-cognitive thinking. The benchmark focuses on coloring odd cycle graphs ($C_3, C_5, C_{11}$) with limited colors, where deterministic, non-communicating agents fail in infinite loops. A strategy passing mechanism is implemented as a form of consistent memory. We show that while standard LLMs and classical heuristics struggle, advanced reasoning models (e.g., O3) devise strategies to escape deadlocks. LoopBench allows the study of emergent distributed algorithms based on language-based reasoning, offering a testbed for collective intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms
Parsaee, Ali
Talebirad, Yashar
Szepesvári, Csongor
Ohal, Vishwajeet
Redman, Eden
Artificial Intelligence
Machine Learning
Multiagent Systems
Large Language Models (LLMs) are increasingly being utilized as autonomous agents, yet their ability to coordinate in distributed systems remains poorly understood. We introduce \textbf{LoopBench}, a benchmark to evaluate LLM reasoning in distributed symmetry breaking and meta-cognitive thinking. The benchmark focuses on coloring odd cycle graphs ($C_3, C_5, C_{11}$) with limited colors, where deterministic, non-communicating agents fail in infinite loops. A strategy passing mechanism is implemented as a form of consistent memory. We show that while standard LLMs and classical heuristics struggle, advanced reasoning models (e.g., O3) devise strategies to escape deadlocks. LoopBench allows the study of emergent distributed algorithms based on language-based reasoning, offering a testbed for collective intelligence.
title LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms
topic Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2512.13713