Get Started
Home
Topics
Search
Library
Research questionHow can multi-agent LLM systems sustain autonomous exploration and knowledge accumulation in open-ended discovery?Open-ended discovery requires search to continue beyond fixed heuristics while useful findings accumulate and guide later work. Multiple agents also need to coordinate their exploration as the search evolves.
AI
AI Agents
AI Memory
Multi-agent Systems
Neural and Evolutionary Computing
Latest papersRecent research connected to this question, newest first.CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended DiscoveryThe source studies CORAL, a long-running asynchronous multi-agent LLM evolution framework with shared persistent memory and heartbeat-based interventions. Evidence comes from mathematical, algorithmic, and systems optimization tasks, including a kernel-engineering task, with comparisons against fixed evolutionary-search baselines and analyses of knowledge reuse and agent communication.research paper · Sep 2, 2026
Related questions
How can multimodal language-model agents coordinate hidden prerequisites during long-horizon open-world exploration?How can LLM orchestrators preserve continuous state when collaborating with non-language agents?How can LLM agents jointly adapt reasoning policies and hierarchical skill libraries during reinforcement learning?How can LLM agents generalize to unseen tasks without directly fine-tuning their policies?