Harness-S trains agents using sibling harnesses
It selectively rescues failures with sibling harnesses and transfers capabilities to the base policy.
Stories per day · 30 days
5 stories, newest first · one card per story
Stories tagged #harness-evolution
TinyAstral distills harness improvements to 4B robot agents
TinyAstral transfers gains from large teacher harnesses to compact students reaching near teacher performance on manipulation tasks.
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
Video-RSI lets video agents rewrite their own harnesses, improving accuracy while inspecting fewer frames.
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Research shows imitation of expert trajectories breaks weaker models' harness fit, while on-policy expert correction preserves gains across seven enterprise agent tasks.
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?
Researchers introduce EVOHARNESSBENCH, a benchmark showing that evolving agent harnesses (tools, skills, agents) cause forgetting and inconsistent adaptation across 802 tasks.