1
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
LLM智能体新范式：让模型权重与“缰绳”协同进化，提升适应性与性能。
arXiv:2607.22688v1 Announce Type: cross Abstract: Post-training agents for automated AI research requires optimizing not only model parameters, but al…