3 papers
cs.CL2026
Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
Bin Wu, Guanyun Zou, Bingbing Wang +2
A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep w…
cs.SE2026
Agentic Verification of Software Systems
Haoxin Tu, Huan Zhao, Yahui Song +3
Automatically generated code is gaining traction recently, owing to the prevalence of Large Language Models (LLMs). Further, the AlphaProof initiative has demonstrated the possibil…
cs.SE2026
Automated Lemma Discovery in Agentic Program Verification
Huan Zhao, Haoxin Tu, Zhengyao Liu +3
Deductive verification provides strong correctness guarantees for code by extracting verification conditions (VCs) and writing formal proofs for them. The expertise-intensive task…