2 papers
cs.AI2026
RobustSGPO: Search-Space Control for Agent Harness Evolution
Zibo Zhao, Jijun Shi, Mo Zhou +9
Semantic-gradient-based prompt optimization (SGPO) improves agent harnesses using execution feedback, but its local update rule leaves the choice of edit scope and operation unreso…
cs.AI2026
LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories
Yunfei Zhang, Boyu Feng, Changhua Pei +14
In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed across the history. Short histories of…