Tag
Introduces EvoHarness-RL, a framework that learns runtime harness policies for long-horizon LLM agents, enabling them to construct and update external state (belief, progress, experience) during task execution. Using Qwen3-8B on ALFWorld, it achieves 96.9% success and reveals harness annealing and evolution dynamics.
Harness-R1 introduces a method that learns to edit executable runtime harnesses for LLM agents from failure trajectories, using a separate 9B engineer optimized with online GRPO while keeping the target model frozen. It improves success rates across WebShop, ALFWorld, and DBBench.
Proposes Life-Harness, a method that improves frozen LLM agents by adapting the runtime interface instead of model weights, achieving an average 88.5% relative improvement across 126 settings and 18 backbones.