OSU NLP Group Wins Three Paper Awards Same Day at EMNLP 2026 and NeurIPS Workshop
hhsun1 · x · 2026-10-28
The OSU/Penn NLP group announces multiple awards: SkillHarm (EMNLP Outstanding Paper) introduces Self-Mutating Poisoning, where benign execution silently corrupts persistent agent skill content to defer harm until reuse. D3-Gym (EMNLP Outstanding Paper) builds scientific task environments for training discovery agents, already attracting startup interest. AgentCL won Runner-up at the NeurIPS 2026 TTCL workshop for rigorous evaluation of continual learning in language agents.
More from coding & agent
- CodeRabbit Secure adds cross-repo Deep Scan, sandbox exploit verification and merge blocking — nevrekaraishwa2 · 2026-10-28
- Hyphenate raises $45M Series A after 86x revenue growth as agents run 90% of finance work — ahuja_priyank · 2026-10-28
- Open-source anymove turns one AI video into motion capture for any creature at $0.26 per clip — noahsolomon · 2026-10-28
- When to stop correcting an AI agent and restart the task instead — ZinchaDEV · 2026-10-28
- MASS paper: one model plays the whole agent team to bootstrap recursive self-improvement — idanbeck · 2026-10-28
- Dev builds AI-native macOS dock where an agent classifies activity and notifications in real time — trq212 · 2026-10-28