Cover Image

RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Yiyou, Cao, Yuhan, Huang, Pohao, Bai, Haoyue, Hajishirzi, Hannaneh, Dziri, Nouha, Song, Dawn
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
by: Sun, Yiyou, et al.
Published: (2025)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
by: Sun, Yiyou, et al.
Published: (2025)

TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities
by: Graf, Victoria, et al.
Published: (2026)

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
by: Sun, Yiyou, et al.
Published: (2025)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
by: Zhao, Bowen, et al.
Published: (2024)

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
by: Zhang, Xiangxiang, et al.
Published: (2026)

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them
by: Zhang, Weichen, et al.
Published: (2025)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
by: Li, Ziniu, et al.
Published: (2025)

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
by: He, Bingxiang, et al.
Published: (2025)

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
by: Cao, Qingqing, et al.
Published: (2023)

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis
by: Bennion, Jonathan, et al.
Published: (2025)

Vero: An Open RL Recipe for General Visual Reasoning
by: Sarch, Gabriel, et al.
Published: (2026)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
by: Wiegreffe, Sarah, et al.
Published: (2024)

How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns
by: Bai, Haoyue, et al.
Published: (2025)

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
by: Pouplin, Thomas, et al.
Published: (2024)

ScienceMeter: Tracking Scientific Knowledge Updates in Language Models
by: Wang, Yike, et al.
Published: (2025)

Can LLMs Ask Good Questions?
by: Zhang, Yueheng, et al.
Published: (2025)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
by: Liu, Mingjie, et al.
Published: (2025)

HREF: Human Response-Guided Evaluation of Instruction Following in Language Models
by: Lyu, Xinxi, et al.
Published: (2024)

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
by: Kim, Joongwon, et al.
Published: (2024)

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
by: Han, Seungju, et al.
Published: (2024)

The Art of Saying No: Contextual Noncompliance in Language Models
by: Brahman, Faeze, et al.
Published: (2024)

Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance
by: Liang, Weida, et al.
Published: (2026)

EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
by: Zeng, Zhiyuan, et al.
Published: (2025)

MentorCollab: Selective Large-to-Small Inference-Time Guidance for Efficient Reasoning
by: Wang, Haojin, et al.
Published: (2026)

ToRL: Scaling Tool-Integrated RL
by: Li, Xuefeng, et al.
Published: (2025)

Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
by: Chen, Tong, et al.
Published: (2025)

Set the Clock: Temporal Alignment of Pretrained Language Models
by: Zhao, Bowen, et al.
Published: (2024)

Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index
by: Xu, Hao, et al.
Published: (2025)

RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
by: Huang, Jerry, et al.
Published: (2025)

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
by: Shu, Fangxun, et al.
Published: (2025)

Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
by: Liu, Jiacheng, et al.
Published: (2024)

Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
by: Tran, Hieu, et al.
Published: (2025)

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
by: Lin, Bill Yuchen, et al.
Published: (2024)

Organize the Web: Constructing Domains Enhances Pre-Training Data Curation
by: Wettig, Alexander, et al.
Published: (2025)

Steering off Course: Reliability Challenges in Steering Language Models
by: Da Silva, Patrick Queiroz, et al.
Published: (2025)

ComPO: Community Preferences for Language Model Personalization
by: Kumar, Sachin, et al.
Published: (2024)

Small Reward Models via Backward Inference
by: Wang, Yike, et al.
Published: (2026)

ReviewRL: Towards Automated Scientific Review with RL
by: Zeng, Sihang, et al.
Published: (2025)

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
by: Hanqing, Liu, et al.
Published: (2026)