Cover Image

You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Roy, Shuvendu, Hajimirsadeghi, Hossein, Zhai, Mengyao, Samei, Golnoosh
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Were RNNs All We Needed?
by: Feng, Leo, et al.
Published: (2024)

RL for Reasoning by Adaptively Revealing Rationales
by: Amani, Mohammad Hossein, et al.
Published: (2025)

Label-Free Reinforcement Learning via Cross-Model Entropy
by: Gorbett, Matt, et al.
Published: (2026)

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
by: Pan, Teng, et al.
Published: (2026)

Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models
by: Gomaa, Eyad, et al.
Published: (2024)

Token-Efficient RL for LLM Reasoning
by: Lee, Alan, et al.
Published: (2025)

rePIRL: Learn PRM with Inverse RL for LLM Reasoning
by: Wu, Xian, et al.
Published: (2026)

When Can LLMs Learn to Reason with Weak Supervision?
by: Rahman, Salman, et al.
Published: (2026)

Synthetic Data RL: Task Definition Is All You Need
by: Guo, Yiduo, et al.
Published: (2025)

Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
by: Potamitis, Nearchos, et al.
Published: (2025)

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
by: Mao, Yixiu, et al.
Published: (2026)

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
by: Ran-Milo, Yuval, et al.
Published: (2026)

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
by: Stoisser, Josefa Lia, et al.
Published: (2025)

Radar: Fast Long-Context Decoding for Any Transformer
by: Hao, Yongchang, et al.
Published: (2025)

Accelerating RL for LLM Reasoning with Optimal Advantage Regression
by: Brantley, Kianté, et al.
Published: (2025)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
by: Qu, Yun, et al.
Published: (2025)

Reasoning with Sampling: Your Base Model is Smarter Than You Think
by: Karan, Aayush, et al.
Published: (2025)

On the Optimal Reasoning Length for RL-Trained Language Models
by: Nohara, Daisuke, et al.
Published: (2026)

Attention is All You Need Until You Need Retention
by: Yaslioglu, M. Murat
Published: (2025)

LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
by: Kang, Haoqiang, et al.
Published: (2026)

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner
by: Chang, Fu-Chieh, et al.
Published: (2024)

Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning
by: Harmel, Moritz, et al.
Published: (2023)

Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning
by: Ganesh, Prakhar, et al.
Published: (2025)

Learning to Reason as Action Abstractions with Scalable Mid-Training RL
by: Zhang, Shenao, et al.
Published: (2025)

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
by: Sun, Lin, et al.
Published: (2025)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
by: Cai, Xin-Qiang, et al.
Published: (2026)

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
by: Shrestha, Safal, et al.
Published: (2026)

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
by: Puri, Isha, et al.
Published: (2026)

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
by: Parekh, Swapnil
Published: (2026)

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
by: Mahrooghi, Ilia, et al.
Published: (2026)

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
by: Simmons-Edler, Riley, et al.
Published: (2025)

Base Models Know How to Reason, Thinking Models Learn When
by: Venhoff, Constantin, et al.
Published: (2025)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
by: Mirzadeh, Iman, et al.
Published: (2024)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
by: Qu, Yun, et al.
Published: (2026)

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
by: Kiyani, Shayan, et al.
Published: (2026)

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
by: Liu, Grace, et al.
Published: (2024)

Optimisation Is Not What You Need
by: Ibias, Alfredo
Published: (2025)

Context is All You Need
by: Delanois, Jean Erik, et al.
Published: (2026)

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
by: Wu, Jiahao, et al.
Published: (2026)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
by: Kim, Juno, et al.
Published: (2025)