arXiv AI
Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks
arXiv:2609.33180v2 Announce Type: replace-cross Abstract: As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies...
arXiv AI
Sep 17
Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
arXiv:2609. 18366v1 Announce Type: new Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed target agent.
arXiv AI
Jun 11
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
arXiv:2606. 05922v2 Announce Type: replace Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems.
arXiv AI
Sep 2
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
arXiv AI
Jul 17
Reward-Free Evolving Agents via Pairwise Validator
arXiv:2607. 14408v1 Announce Type: new Abstract: A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality signal.
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.