3 papers
cs.LG2026
On the Off-Policy Teacher in On-Policy Distillation
Langlin Huang, Hao Liu, Mononito Goswami +6
On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teache…
cs.LG2026
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Prithwish Jana, Mononito Goswami, Hao Liu +9
Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance, yet its…
cs.LG2026
Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
Xinyu Li, Mononito Goswami, Hao Liu +5
Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how…