collaborators

10 papers

cs.CL2026

Structured Thoughts For Improved Reasoning And Context Pruning

Zain Sarwar, Supriyo Chakraborty, Berkcan Kapusuzoglu +5

Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured T…

cs.LG2026

On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse

Amritansh Mishra, Supriyo Chakraborty, Berkcan Kapusuzoglu

Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a rigorous derivation of GRPO…

cs.AI2026

Know Thy Reasoner: Not All Language Models Explore Alike

Moulik Choraria, Argyrios Gerogiannis, Anirban Das +4

Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why…

cs.AI2026

A History-Aware Visually Grounded Critic for Computer Use Agents

Jaewoo Lee, Zaid Khan, Archiki Prasad +7

Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in compl…

cs.CL2026

Critique-Guided Distillation for Robust Reasoning via Refinement

Berkcan Kapusuzoglu, Supriyo Chakraborty, Zain Sarwar +2

Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While c…

cs.CR2026

CoT-Guard: Small Models for Strong Monitoring

Nirav Diwan, Han Wang, Berkcan Kapusuzoglu +6

Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large m…