Paper 2604.01658
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
- Published
- Apr 2026
- Research lab
- Independent
- Citations
- 29
- GitHub
- 873 stars
01 In brief
Summary
CORAL is a framework for autonomous multi-agent evolution on open-ended problems, replacing fixed evolutionary search heuristics with long-running LLM agents that control retrieval, proposal, evaluation, and knowledge accumulation.
It uses shared persistent memory (attempts, notes, skills), asynchronous multi-agent execution, and heartbeat-based interventions for reflection, consolidation, and redirection.
Evaluated on mathematical, algorithmic, and systems optimization tasks, CORAL achieves new state-of-the-art results on 8 of 11 tasks, with 3–10x higher improvement rates and fewer evaluations than fixed baselines.
On Anthropic's kernel engineering task, four co-evolving agents improved the best known score from 1363 to 1103 cycles (a 20% gain).
Ablations show that knowledge accumulation and co-evolution (vs.
independent runs) causally contribute to gains.
Gains generalize to open-source models (MiniMax M2.5 + OpenCode).
The framework includes safeguards like isolated workspaces, evaluator separation, and resource management.
02 From the paper
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.