arXiv AI
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 5
VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
The paper introduces VERSE, a Verified Self‑Evolving optimizer that enhances LLM agent harnesses by allowing the optimizer to test edits, replay failures, and perturb steps while tracking fixes and regressions. VERSE builds its own tools for failure analysis, verification, training audits, and workflow control, and uses this feedback to revise the harness’s prompts, skills, tools, hooks, and notes without changing model weights. In experiments across five executors and multiple languages, VERSE improves all evaluated harness optimizers, achieving higher accuracy on held‑out and out‑of‑distribution tasks compared to the strongest baselines.
arXiv AI
Jul 7
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.
arXiv AI
Sep 30
EASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents
arXiv:2609.36746v1 Announce Type: new Abstract: Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. Ho...
arXiv AI
Aug 5
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
arXiv:2608. 02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.
arXiv Computation and Language
Sep 7
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?
EVOHARNESSBENCH is a new benchmark that tests how LLM-based agents handle changes in their tool, skill, and agent harnesses over time. It includes 17 deterministic harness streams with 802 tasks, 520 tools, 42 skills, and 62 agents, and evaluates agents in two settings: deployment evaluation and self‑evolving adaptation evaluation. The study finds that harness expansion can cause forgetting, adaptation gains are inconsistent, and preserving old competence does not always aid new capability adaptation, highlighting harness evolution as a distinct challenge for agent development.
arXiv AI
Aug 11
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses
arXiv:2608. 08466v1 Announce Type: new Abstract: Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment.