Author

Sayak Chakrabarti

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents

Group Relative Policy Optimization (GRPO) avoids a separate critic by estimating advantages from rollout groups. For multi-turn agents, however, trajectory-level supervision provides coarse, noisy credit: terminal rewards do not locate errors and can penalize useful actions alongside mistakes. Group-in-Group Policy Opt...

Sayak Chakrabarti, Sathish Indurthi · 0 citations

#artificial intelligence Feb 2026

Poly-attention: a general scheme for higher-order self-attention

This work defines a vast class of generalizations of self-attention mechanisms, which they are called poly-attention mechanisms, and gives a new attention mechanism which can be computed exactly in quadratic time, and which can perform function composition for any fixed number of functions.

Sayak Chakrabarti, T. Pitassi, Josh Alman · arXiv.org · 3 citations