← Back to all news
arXiv AI By Aishik Nagar, Cheston Tan

Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models

Read the original on arXiv AI →

The paper investigates whether reinforcement learning (RL) truly endows large language models (LLMs) with reasoning skills or merely tunes them to exploit prompt information. By training small LLMs on the finite logical domain of Tic‑Tac‑Toe and applying Group Relative Policy Optimization (GRPO), the authors show that RL improves accuracy and robustness. However, mechanistic interpretability using sparse autoencoders reveals that the models mainly rely on explicit prompt cues—such as turn order, game progression, and board occupancy—while higher‑level concepts like board symmetries and strategic forks remain weakly represented, suggesting that perceived reasoning may be an artifact of task‑specific adaptations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 31

Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models

arXiv:2607. 26119v1 Announce Type: new Abstract: Large reasoning models trained via reinforcement learning (RL) have been increasingly shown to outperform their supervised fine-tuned (SFT) counterparts on mathematical reasoning tasks; Yet the mechanistic basis for this advantage remains unclear.

By Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit, Kevin Zhu, Aishwarya Balwani
reinforcement-learningfine-tuningbenchmarks
More like this →
arXiv AI
Aug 18

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.

By Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu
llmsreinforcement-learningfine-tuningsafetydata-engineering
More like this →
arXiv AI
Jun 18

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

arXiv:2606. 18521v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting.

By Chenrui Wu, Zexi Li, Jiajun Bu, Jiangchuan Liu, Haishuai Wang
reinforcement-learningfine-tuningefficiencybenchmarks
More like this →
arXiv AI
Oct 7

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

Rationale-Guided Policy Optimization (RGPO) is a reinforcement‑learning framework that adaptively uses ground‑truth rationale information to scaffold a language model’s reasoning process. Instead of treating reference solutions as fixed imitation targets, RGPO temporarily incorporates rationales to help the model generate better responses, then reverts to unguided learning with higher‑reward, model‑generated solutions. Experiments in both language‑only and vision‑language tasks show that RGPO consistently outperforms RLVR baselines, with ablation studies confirming that adaptive rationale guidance is a key factor in its success.

By Hoang Phan, Minh Pham, Chau Pham, Chinmay Hegde, Trung Le, Qi Lei
llmsreinforcement-learningefficiencymultimodalbenchmarks
More like this →