2 papers
cs.AI2026
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
Sarthak Harne, Chinmay Karkar, Yash Pandya +2
Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI)…
cs.CL2026
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Aradhye Agarwal, Gurdit Siyan, Yash Pandya +3
Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, su…