news

Oct 26, 2026 At EMNLP 2026, where Steer, Don’t Solve is presented as an oral.
Oct 22, 2026 Three new preprints on securing web applications with LLM agents: ABSENTIA, Self-Evolving Static Analysis, and Ulysses.
Sep 05, 2026 New preprint from my IBM Research internship: DRACO, fine-grained credit assignment with dynamic rubrics for long-horizon agent training.
Sep 04, 2026 Steer, Don’t Solve, on training small critic models for large code agents, is accepted to EMNLP 2026 as an oral presentation!
Sep 01, 2026 Evaluating Code Slop in Long-Horizon Coding Agents is accepted at the Workshop on Agent Behavior at COLM 2026.
Aug 24, 2026 Started my Ph.D. in Language Technologies at CMU! :tada:
May 01, 2026 Hybrid-Gym, on training coding agents to generalize across tasks, is accepted to ICML 2026.
Jan 15, 2026 Leading the CMU red team in the Amazon Nova AI Challenge 2026, Trusted Software Agents track. Our team received a $250K research grant.
Dec 15, 2025 Completed my M.S. in Intelligent Information Systems at CMU.
Sep 22, 2025 When Agents go Astray, on course-correcting SWE agents with process reward models, is accepted at the SEA Workshop at NeurIPS 2025.
Aug 20, 2025 Our paper on strong-weak model collaboration for repo-level code generation is accepted to EMNLP 2025.