HarnessPro: Label-Free Recursive Harness Self-Improvement Balancing Agent Performance and Cost
Zhuoshi Pan · hf · 2026-10-20
Researchers from Tsinghua, SJTU, Kuaishou and others introduce HarnessPro, a label-free method that recursively evolves agent harnesses via Pareto optimization over performance-cost trade-offs.
- Candidate harnesses are evaluated with LLM-generated tests, no ground-truth or official tests needed
- Specialized agents diagnose execution trajectories and propose plan updates as new candidates
- Normalized weighted squared-distance selection yields cost-focused (lite), balanced (medium), and performance-focused (heavy) harnesses for different deployment budgets
More from coding & agent
- Indie dev says AI removed the model bottleneck: solo-building a physics excavator sim — Michael_J_Black · 2026-10-20
- HSPR Recovers Full Agent Benchmark Scores From Small Subsets via Hierarchical Posterior Inference — SUDA · 2026-10-20
- AdaExploreBench Finds LLM Agents Struggle at Proactive Exploration in Evolving Environments — HKUST · 2026-10-20
- Our OAuth discovery doc and Python docs give agents opposite signup instructions — bshivarthy · 2026-10-20
- Fo launches MCP to let AI agents control and sense physical devices, 100+ devs already building — heyshrutimishra · 2026-10-20
- Open-source humanoid Asimov 1 ships docs: assembly guides, sim-to-real training, browser demo — Sentdex · 2026-10-20