most citedPosition: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

4 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

cs.AI2026

Masked Distillation: Internalizing the Chain-of-Thought in Language Models

Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati

Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate traces dominate latency, me…

cs.AI20264 cited

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Subbarao Kambhampati, Karthik Valmeekam, Siddhant Bhambri +6

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning task…

cs.RO2026

NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming

Upasana Biswas, Durgesh Kalwar, Subbarao Kambhampati +1

Mutual adaptation is a central challenge in human-AI teaming, as humans naturally adjust their strategies in response to an AI agent's behavior. Existing approaches attempt to appr…

cs.LG2026

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs

Soumya Rani Samineni, Durgesh Kalwar, Karthik Valmeekam +2

Reinforcement learning based post-training of large language models (LLMs) has recently gained attention, particularly following the release of DeepSeek R1, which applied GRPO for…

cs.AI2025

Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains

Soumya Rani Samineni, Durgesh Kalwar, Vardaan Gangal +2

Reinforcement Learning with Verifiable Rewards (RLVR)-based post-training of Large Language Models (LLMs) has been shown to improve accuracy on reasoning tasks and continues to att…

cs.LG2025

Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead

Durgesh Kalwar, Mayank Baranwal, Harshad Khadilkar

In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes…