MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

• URL: http://arxiv.org/abs/2603.17187v1
• Date: Tue, 17 Mar 2026 22:30:30 GMT
• Title: MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
• Abstract summary: Large language model (LLM) agents are increasingly used for complex tasks.<n>Existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining.<n>We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills.
• Score: 74.7263562191605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.

Related papers

• SPyCE: Skill-Policy Co-evolution for Multimodal Agents [12.105041985483167]
  We propose SPyCE, a framework that distills trajectories into a hierarchical skill library and updates it throughout reinforcement learning.<n>During training, the policy model conditions on retrieved skills to guide its rollouts, while the skill library evolves using valuable rollouts generated by the policy.<n> Experiments across eight benchmarks demonstrate that SPyCE consistently outperforms both RL-based and memory-based baselines.
  arXiv  Detail & Related papers  (2026-07-15T14:01:48Z)
• Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach [12.79484512803839]
  Large language model (LLM) agents are increasingly extended through Agent Skills.<n>As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills.<n>We propose Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL) to detect cross-layer misalignment.
  arXiv  Detail & Related papers  (2026-07-12T02:07:37Z)
• You Live More Than Once: Towards Hierarchical Skill Meta-Evolving [92.6633152185458]
  Test-time skill evolving is regarded as a new paradigm for enhancing agentic systems.<n>We show that test-time refinement of the skill evolving framework is necessary for continuous improvement of the agent systems.<n>We propose HiSME, a lightweight hierarchical skill meta-evolving solution.
  arXiv  Detail & Related papers  (2026-05-27T12:26:49Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use [50.52940111891476]
  Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools.<n>We present RLFactory, a plug-and-play reinforcement learning framework for multi-round tool use.
  arXiv  Detail & Related papers  (2025-08-31T16:47:31Z)
• Memento: Fine-tuning LLM Agents without Fine-tuning LLMs [36.3424780932712]
  We introduce a novel learning paradigm for Adaptive Large Language Model (LLM) agents.<n>Our method enables low-cost continual adaptation via memory-based online reinforcement learning.<n>We instantiate our agent model in the deep research setting, namely emphMemento, which attains top-1 on GAIA validation.
  arXiv  Detail & Related papers  (2025-08-22T07:25:30Z)
• Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agent [7.631972490231939]
  We introduce WIRL, an agent for code wiring framed as a Retrieval-Augmented Generation (RAG) infilling task.<n>We evaluate WIRL on a carefully curated, high-quality dataset consisting of real-world code adaptation scenarios.
  arXiv  Detail & Related papers  (2025-07-02T03:00:23Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Meta Reinforcement Learning for Adaptive Control: An Offline Approach [3.131740922192114]
  We formulate a meta reinforcement learning (meta-RL) control strategy that takes advantage of known, offline information for training. Our meta-RL agent has a recurrent structure that accumulates "context" for its current dynamics through a hidden state variable. In tests reported here, the meta-RL agent was trained entirely offline, yet produced excellent results in novel settings.
  arXiv  Detail & Related papers  (2022-03-17T23:58:52Z)

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.