10 papers
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
Jiaqi Shao, Hanck Chen, Wei Zhang +2
Agent benchmarks increasingly evaluate repository editing, web research, terminal use, and long-horizon interaction. Their scores support capability claims only when the evaluation…
Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows
Yuhang Fu, Ruishan Fang, Jiaqi Shao +4
Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging? We intro…
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
Jiaqi Shao, Yiyi Lu, Yunzhen Zhang +1
Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not anno…
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
Suning Huang, Jiaqi Shao, Ke Wang +5
Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limit…
FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
Jiaqi Shao, Yufeng Miao, Wei Zhang +1
Long-horizon reinforcement learning (RL) for large language models faces critical scalability challenges from unbounded context growth, leading to context folding methods that comp…
Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Jiaqi Shao, Yuxiang Lin, Munish Prasad Lohani +2
Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering (QA). However, most evaluations focus…