RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
Fuente:
arXiv
Saved in:
| Main Authors: | Sun, Yiyou, Cao, Yuhan, Huang, Pohao, Bai, Haoyue, Hajishirzi, Hannaneh, Dziri, Nouha, Song, Dawn |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| 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)
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)
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)
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)
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)
by: Zhao, Bowen, et al.
Published: (2024)
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
by: Zhang, Xiangxiang, et al.
Published: (2026)
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)
by: Zhang, Weichen, et al.
Published: (2025)
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
by: Li, Ziniu, et al.
Published: (2025)
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)
by: He, Bingxiang, et al.
Published: (2025)
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
by: Cao, Qingqing, et al.
Published: (2023)
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)
by: Bennion, Jonathan, et al.
Published: (2025)
Vero: An Open RL Recipe for General Visual Reasoning
by: Sarch, Gabriel, et al.
Published: (2026)
by: Sarch, Gabriel, et al.
Published: (2026)
Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
by: Wiegreffe, Sarah, et al.
Published: (2024)
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)
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)
by: Pouplin, Thomas, et al.
Published: (2024)
ScienceMeter: Tracking Scientific Knowledge Updates in Language Models
by: Wang, Yike, et al.
Published: (2025)
by: Wang, Yike, et al.
Published: (2025)
Can LLMs Ask Good Questions?
by: Zhang, Yueheng, et al.
Published: (2025)
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)
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)
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)
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)
by: Han, Seungju, et al.
Published: (2024)
The Art of Saying No: Contextual Noncompliance in Language Models
by: Brahman, Faeze, et al.
Published: (2024)
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)
by: Liang, Weida, et al.
Published: (2026)
EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
by: Zeng, Zhiyuan, et al.
Published: (2025)
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)
by: Wang, Haojin, et al.
Published: (2026)
ToRL: Scaling Tool-Integrated RL
by: Li, Xuefeng, et al.
Published: (2025)
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)
by: Chen, Tong, et al.
Published: (2025)
Set the Clock: Temporal Alignment of Pretrained Language Models
by: Zhao, Bowen, et al.
Published: (2024)
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)
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)
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)
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)
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)
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)
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)
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)
by: Da Silva, Patrick Queiroz, et al.
Published: (2025)
ComPO: Community Preferences for Language Model Personalization
by: Kumar, Sachin, et al.
Published: (2024)
by: Kumar, Sachin, et al.
Published: (2024)
Small Reward Models via Backward Inference
by: Wang, Yike, et al.
Published: (2026)
by: Wang, Yike, et al.
Published: (2026)
ReviewRL: Towards Automated Scientific Review with RL
by: Zeng, Sihang, et al.
Published: (2025)
by: Zeng, Sihang, et al.
Published: (2025)
Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
by: Hanqing, Liu, et al.
Published: (2026)
by: Hanqing, Liu, et al.
Published: (2026)
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)