arXiv AI June 2, 2026 By Zihan Chen, Yiming Zhang, Wenxiang Geng, Zenghui Ding, Yining Sun

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs

arXiv:2606. 00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reasoning capabilities on out-of-distribution (OOD) tasks.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 29

The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment

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

llms reinforcement-learning benchmarks

arXiv AI

Jun 29

CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching

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

llms benchmarks

arXiv AI

Aug 11

TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation

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

llms agents benchmarks

arXiv Machine Learning

Jun 9

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

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

safety

arXiv Machine Learning

Jun 9

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

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

llms reinforcement-learning

arXiv AI

Jun 10

Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought

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

llms reinforcement-learning

Related stories

The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment

CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching

TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought