3 accepted papers
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-t…
Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering—a paradigm where models autonomously navigate, edit, and test complex repositories. While post-training methods have become the de facto approach for code ag…
Motivated by the first priority of safety in many real-world applications, we propose \textsc{MaxSafe}, a chance-constrained bi-level optimization framework for safe reinforcement learning. \textsc{MaxSafe} first minimizes the unsafe probability and then maximizes the return among the safest policie…