Kishan Panaganti

kishanpb

·

https://sites.google.com/a/tamu.edu/kpb/home

AI & ML interests

LLM Reasoning via RL and anything RL

Recent Activity

upvoted a paper about 14 hours ago

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

upvoted a paper 28 days ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

authored a paper 29 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

View all activity

Organizations

None yet

kishanpb 's papers 7

arxiv:2607.13285

arxiv:2601.19280

arxiv:2512.15687

arxiv:2512.02472

arxiv:2510.20187

arxiv:2509.15194

arxiv:2506.11302