2 papers
cs.AI2026
Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts
Jianghan Shen, Zhenjie Liu, Yue Li +10
Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases and env…
cs.SE2026
AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
Yiming Cheng, Alfin Wijaya Rahardja, Mengshi Zhang +3
Agent harness bugs exhibit unique characteristics and remain challenging for state-of-the-art software agents to repair. Progress in this area is further hindered by existing bench…