arXiv AI
CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
2d ago
EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems
arXiv:2610.34450v1 Announce Type: cross Abstract: Decentralized multi-agent systems (MAS) enable large language model agents to interact without centralized control. Agents need to adapt to other age...
arXiv AI
Oct 19
Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents
Darwin‑Claw is a new framework for large language model agents that enables environment‑adaptive, self‑evolving behavior. It systematically distills episodic experiences into prototype vectors through a hierarchical experience consolidation system, providing context‑sensitive perception patches and explicit optimization signals for skill refinement. The method is deployable with mainstream agent systems and, according to experiments on WildClawBench, delivers significant performance gains while maintaining controllability and stability.
arXiv AI
Aug 11
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
arXiv:2604. 08377v2 Announce Type: replace Abstract: Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment.
arXiv Computation and Language
Sep 14
LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, e...
arXiv AI
Oct 15
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
arXiv:2605.29790v2 Announce Type: replace-cross Abstract: LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, M...
arXiv Computation and Language
Sep 21
MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.