EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

• URL: http://arxiv.org/abs/2605.11136v1
• Date: Mon, 11 May 2026 18:42:33 GMT
• Title: EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
• Abstract summary: A single-agent learner can only evolve its own context and memory.<n>A multi-agent system additionally evolves who collaborates, how they collaborate, and how knowledge flows across the population.<n>We present EVOCHAMBER, a training-free framework that instantiates test-time evolution at three levels over a coevolving agent pool.
• Score: 27.568287645700064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We argue that multi-agent test-time evolution is not single-agent evolution replicated N times. A single-agent learner can only evolve its own context and memory. A multi-agent system additionally evolves who collaborates, how they collaborate, and how knowledge flows across the population. These components have no single-agent counterpart and can produce phenomena such as emergent specialization. Yet prior test-time methods either confine experiences to individual agents, forfeiting cross-agent learning, or broadcast symmetrically to all agents, erasing the specialization that makes collaboration valuable. We present EVOCHAMBER, a training-free framework that instantiates test-time evolution at three levels over a coevolving agent pool. At its core is CODREAM (Collaborative Dreaming), a post-task protocol triggered on team failure or disagreement, in which agents collaboratively reflect, distill insights, and route them asymmetrically from strong to weak agents on the failed niche, preserving specialization while filling knowledge gaps. Team-level operators assemble niche-conditioned teams and select collaboration structures online. Population-level lifecycle operators fork, merge, prune, and seed agents under performance pressure. On three heterogeneous task streams with Qwen3-8B, EVOCHAMBER reaches 63.9% on competition math, 75.7% on code, and 87.1% on multi-domain reasoning, outperforming the best baseline by 32% relative on math and confirming asymmetric cross-agent transfer as the primary driver in ablation. Starting from several identically initialized agents, four to five stable niche specialists spontaneously emerge, a structural signature of multi-agent evolution that no single-agent learner can express. See our code at: https://github.com/Mercury7353/EvoChamber

Related papers

• Benchmarking Open-Ended Multi-Agent Coordination in Language Agents [48.1363632826625]
  Alem embeds procedurally generated coordination tasks, soft specialisation, communication, and controllable coordination difficulty into a long-horizon survival world.<n>We introduce $alem$, a JAX-based benchmark for open-ended multi-agent coordination built on Craftax-like dynamics.
  arXiv  Detail & Related papers  (2026-06-06T21:13:43Z)
• AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization [46.78426363253909]
  We introduce AgentPSO, a framework for evolving multi-agent reasoning skills.<n>AgentPSO treats each agent as a particle-like reasoner whose state is a natural-language skill.<n>It iteratively moves agents toward stronger skill states to improve both individual and collective reasoning performance.
  arXiv  Detail & Related papers  (2026-05-09T05:38:21Z)
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery [67.47220507982522]
  Large language model (LLM)-based evolution is a promising approach for openended discovery.<n>We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems.<n>CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate.
  arXiv  Detail & Related papers  (2026-04-02T05:59:06Z)
• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning [112.16686518063456]
  We introduce textbfMulti-Agent Test-Time Reinforcement Learning (MATTRL), a framework that injects structured textual experience into multi-agent deliberation at inference time.<n>MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making.<n>Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67% over a multi-agent baseline, and by 8.67% over comparable single-agent baselines
  arXiv  Detail & Related papers  (2026-01-14T17:57:43Z)
• Emergent Coordination in Multi-Agent Language Models [2.504366738288215]
  We introduce an information-theoretic framework to test whether multi-agent systems show signs of higher-order structure.<n>This information decomposition lets us measure whether dynamical emergence is present in multi-agent LLM systems.<n>We apply our framework to experiments using a simple guessing game without direct agent communication.
  arXiv  Detail & Related papers  (2025-10-05T11:26:41Z)
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments [116.97648507802926]
  Large language models (LLMs) are considered a promising foundation to build such agents. We take the first step towards building generally-capable LLM-based agents with self-evolution ability. We propose AgentGym, a new framework featuring a variety of environments and tasks for broad, real-time, uni-format, and concurrent agent exploration.
  arXiv  Detail & Related papers  (2024-06-06T15:15:41Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Multi-Agent Collaboration via Reward Attribution Decomposition [75.36911959491228]
  We propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge. CollaQ is evaluated on various StarCraft Attribution maps and shows that it outperforms existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2020-10-16T17:42:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.