most citedOptimalThinkingBench: Evaluating Over and Underthinking in LLMs

1 citations · 1 across the 4 of their papers we have counts for

collaborators

7 papers

cs.AI2025

Scaling Agent Learning via Experience Synthesis

Zhaorun Chen, Zhuokai Zhao, Kai Zhang +15

While reinforcement learning (RL) can empower autonomous agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts,…

cs.CL2025

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Leitian Tao, Ilia Kulikov, Swarnadeep Saha +5

Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable,…

cs.CL2025

The Majority is not always right: RL training for solution aggregation

Wenting Zhao, Pranjal Aggarwal, Swarnadeep Saha +3

Scaling up test-time compute, by generating multiple independent solutions and selecting or aggregating among them, has become a central paradigm for improving large language model…

cs.CL20251 cited

OptimalThinkingBench: Evaluating Over and Underthinking in LLMs

Pranjal Aggarwal, Seungone Kim, Jack Lanchantin +4

Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder…

cs.CL2025

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

Chenxi Whitehouse, Tianlu Wang, Ping Yu +4

The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thoug…

cs.LG2025

LLM Pretraining with Continuous Concepts

Jihoon Tack, Jack Lanchantin, Jane Yu +7

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perpl…