@OpenHandsDev: Check out this new OpenHands research on skill refinement!
Summary
OpenHands researchers introduce SkillRefiner, an offline method that automatically refines agent skills from existing execution traces, rather than requiring new rollouts.
View Cached Full Text
Cached at: 10/03/26, 11:03 PM
Check out this new OpenHands research on skill refinement!
Really cool to see what the http://Build.One team is building on top of OpenHands! 👏
Users describe the business app they need, and agents assemble it from IT-approved components, while respecting existing permissions and controls.
OpenHands powers the agent layer underneath.
A great example of agents becoming infrastructure inside the products and workflows people already use.
Similar Articles
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.
OpenSkill: Open-World Self-Evolution for LLM Agents
OpenSkill is a framework for LLM agents to self-evolve skills and verification signals from open-world resources without target-task supervision, achieving high performance across benchmarks.
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
SkillHEX proposes a closed-loop framework for autonomous skill evolution in LLM agents, using hypothesis-driven self-verification and evidence-guided tree search to overcome sparse reward challenges. It outperforms existing self-evolving methods on SkillsBench with limited interaction budgets.
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
SkillHone is a harness for continual agent skill evolution that uses persistent decision history and practice feedback to improve performance on research and tool-mediated analysis tasks. It outperforms existing methods on GAIA and WebWalkerQA-EN benchmarks.
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
SkillForge proposes an agentic reinforcement learning method that co-evolves an LLM agent and its skill library through a fitness-driven lifecycle of trial, active, stable, and retired states. It reports up to 7.8% relative improvement over strong baselines on interactive agent benchmarks and releases SkillFurnace, a 5k+ record dataset for studying skill quality and lifecycle management.