CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

TL;DR

CORAL introduces an autonomous multi-agent evolution framework that enhances open-ended discovery by enabling agents to explore, reflect, and collaborate with shared memory, leading to state-of-the-art results across diverse tasks.

Contribution

It presents the first framework for autonomous multi-agent evolution, replacing fixed heuristics with persistent, collaborative agents for open-ended problem solving.

Findings

Achieved 3-10x higher improvement rates than fixed baselines.

Set new state-of-the-art on 10 diverse tasks.

Improved kernel engineering score from 1363 to 1103 cycles.

Abstract

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.