The paper "Demystifying Reinforcement Learning Post-Training of Language Models" investigates how reinforcement learning (RL) post‑training enhances large language models (LLMs) for tasks such as reasoning, math, and coding. By isolating RL components in a controlled setting, the authors analyze how the base model’s prior distribution, reward granularity, prompt diversity, and model scale influence outcomes, using policy entropy to compare pre‑training, supervised fine‑tuning (SFT), and RL stages. The study clarifies the role of spurious rewards, the importance of the base model’s probability mass on desired behaviors, and how these factors interact to determine post‑training success, offering a practical primer for NLP researchers.
"whyItMatters":"The work provides a clearer understanding of RL post‑training mechanics, helping researchers and practitioners effectively apply RL to improve LLM capabilities."
By Donovan Clay, Saket Gollapudi, Sankar Harilal, Min Jang, Jacob Morrison, Sewoong Oh, Natasha Jaques
arXiv:2606. 26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak.
By Jingyu Liu, Xiaopeng Wu, Kehan Chen, Chuan Yu, Yong Liu
arXiv:2607.08837v4 Announce Type: replace-cross
Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...
By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao
Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key source of this failure as task insensitivity: when faced with similar but distinct tasks, models might apply patterns learned during training and fail to solve the task at hand.
Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective.
arXiv:2608. 08802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA.
By Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng, Chenrui Zhou, Lama Moukheiber, Yixing Ma, Bin Xu, Jiajun Song, Zhenglin Wan, Wangbo Zhao, Jiasheng Tang, Bohan Zhuang, Fan Wang, Yang You
arXiv:2602. 03542v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language.
By Fangru Lin, Valentin Hofmann, Xingchen Wan, Weixing Wang, Zifeng Ding, Anthony G. Cohn, Janet B. Pierrehumbert
arXiv:2609.34187v2 Announce Type: replace-cross
Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...
By Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack
The paper investigates how reinforcement learning can cause large language model agents to adopt shortcut policies for tool use, relying on superficial prompt cues rather than actual task needs. By creating synthetic environments that mix factual QA and math reasoning, the authors show that agents often invoke tools when cues are present, even when those tools are unnecessary, with spurious invocation rates rising up to 39%. They find that shortcut learning occurs mainly when agents have already mastered the target tool and that semantic alignment between cues and tools amplifies the effect. To counter this, they propose a dense, decision-level reward where an LLM judge assesses tool necessity, which reduces cue-driven tool use while maintaining performance.
By Yiwei Yang, Haoxiang Zhang, Bingbing Wen, Yao Lu, Yuchen Wu, Lei Zhang, Julian McAuley, Pan Lu, Bill Howe
arXiv:2607. 06175v1 Announce Type: cross Abstract: Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data.
By Alexander Rombach, Chantale Lauer, Nijat Mehdiyev