CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models proposes a new framework to improve medical reasoning in LLMs. It introduces two key conditions—Causal Sufficiency and Proximal Learnability—to curate high-quality training trajectories, using agreement-based self-verification and dynamic entropy bounds. Experiments on medical multimodal and text-only benchmarks show that CARE outperforms competitors, reducing incorrect reasoning and enhancing training stability.
By Yucheng Zhou, Peng Luo, Qianning Wang, Chengzhong Xu, Jianbing Shen
arXiv:2606. 27739v1 Announce Type: new Abstract: Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive stepwise annotations.
By Tianyu Jia, Yue Fang, Hongxin Ding, Rihong Qiu, Zhibang Yang, Zhijing Wu, Xu Chu, Junfeng Zhao, Yasha Wang
arXiv:2602. 20094v2 Announce Type: replace Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations.
By Yuzhe Wang, Yaochen Zhu, Jundong Li
arXiv:2510. 27544v3 Announce Type: replace Abstract: Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning.
By Nikolaus Holzer, William Fishell, Baishakhi Ray, Mark Santolucito
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
By Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
By Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian, Nihal Sharma, Rizal Fathony, Nam H Nguyen, C. Bayan Bruss, Amrit Singh Bedi, Furong Huang
The paper introduces Causal Shortcut Learning (CSL), a framework that identifies token chains—called causal shortcuts—that guide Diffusion Language Models (DLMs) toward correct reasoning paths. By extracting these shortcuts and applying parallel prioritized masking during training, CSL improves both convergence speed and generation accuracy. Experiments on several reasoning benchmarks and two base models show CSL outperforms existing SFT-variant baselines, achieving an average 1.92% improvement over SFT-only models and up to 4.20% on MATH-500.
By Dian Jin, Kairong Han, Baohong Li, Xinpeng Dong, Zijing Hu, Nuanqiao Shan, Fei Wu, Kun Kuang
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
By Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan
arXiv:2609.37119v1 Announce Type: cross
Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
By Hongyang Li, Xiao Li, Caesar Wu, Said Mammar, Gr\'egoire Danoy, Pascal Bouvry
arXiv:2509. 04027v4 Announce Type: replace Abstract: Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs).
By Zeyu Gan, Hao Yi, Yong Liu
arXiv:2607. 08093v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use.
By Andrej Leban, Yuekai Sun
arXiv:2606. 19750v1 Announce Type: cross Abstract: Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization.
By Darrien McKenzie, Nicklas Hansen, Xiaolong Wang