ClawLoop: Self-Improving Agents via Harness-Native Training Loop
cs.AI, cs.CL
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/openclaw/openclaw
Sources
- Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
- ClawGym: A Scalable Framework for Building Effective Claw Agents
- AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
- WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- Towards General Agentic Intelligence via Environment Scaling
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
- ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
- Training Software Engineering Agents and Verifiers with SWE-Gym
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
- ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
- ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
- Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
- Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
- ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems