Cover Image

On Predictability of Reinforcement Learning Dynamics for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Yuchen, Cao, Ding, Xu, Xin, Yao, Zijun, Huang, Yuqing, Tan, Zhenyu, Zhang, Benyi, Sun, Guangzhong, Liu, Guiquan, Fang, Junfeng
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

On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models
by: Cao, Ding, et al.
Published: (2025)

Locating and Mitigating Gender Bias in Large Language Models
by: Cai, Yuchen, et al.
Published: (2024)

Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts
by: Cai, Yuchen, et al.
Published: (2024)

O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
by: Cai, Yuchen, et al.
Published: (2024)

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
by: Hou, Zhenyu, et al.
Published: (2025)

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
by: Liu, Yantao, et al.
Published: (2024)

Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models
by: Bao, Yicheng, et al.
Published: (2026)

Evaluating Retrieval-Augmented Generation Strategies for Large Language Models in Travel Mode Choice Prediction
by: Xu, Yiming, et al.
Published: (2025)

Effective, Platform-Independent GUI Testing via Image Embedding and Reinforcement Learning
by: Yu, Shengcheng, et al.
Published: (2022)

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
by: Zhang, Jiarui, et al.
Published: (2026)

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
by: Xin, Amy, et al.
Published: (2024)

Large Vision Model-Enhanced Digital Twin with Deep Reinforcement Learning for User Association and Load Balancing in Dynamic Wireless Networks
by: Tao, Zhenyu, et al.
Published: (2024)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

An elementary derivation of 3-cycles for a quadratic map
by: Benyi, Arpad, et al.
Published: (2025)

Floor, ceiling and the space between
by: Bényi, Árpád, et al.
Published: (2025)

Partial degenerate Stirling numbers
by: Bényi, Beáta, et al.
Published: (2026)

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
by: Yi, Jingwei, et al.
Published: (2023)

Teaching Large Language Models to Reason with Reinforcement Learning
by: Havrilla, Alex, et al.
Published: (2024)

Reinforced Lifelong Editing for Language Models
by: Li, Zherui, et al.
Published: (2025)

Scaling Reinforcement Learning for Content Moderation with Large Language Models
by: Firooz, Hamed, et al.
Published: (2025)

Stabilizing Reinforcement Learning for Diffusion Language Models
by: Zhong, Jianyuan, et al.
Published: (2026)

Vision Language Model-Empowered Contract Theory for AIGC Task Allocation in Teleoperation
by: Zhan, Zijun, et al.
Published: (2024)

Signal Watermark on Large Language Models
by: Xu, Zhenyu, et al.
Published: (2024)

Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning
by: Wan, Xu, et al.
Published: (2026)

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking
by: Xin, Amy, et al.
Published: (2024)

Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
by: Zhang, Situo, et al.
Published: (2025)

Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
by: He, Jinghan, et al.
Published: (2026)

Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models
by: Tan, Chee Wei, et al.
Published: (2026)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
by: Sun, Jingwen, et al.
Published: (2026)

$B$-Stirling numbers associated to potential polynomials
by: Adell, José A., et al.
Published: (2024)

S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners
by: Yan, Yuchen, et al.
Published: (2024)

Evaluating Generative Language Models in Information Extraction as Subjective Question Correction
by: Fan, Yuchen, et al.
Published: (2024)

Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring
by: Ding, Qiuyu, et al.
Published: (2025)

Rethinking Agentic Reinforcement Learning In Large Language Models
by: Cui, Fangming, et al.
Published: (2026)

P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
by: Jiang, Guochao, et al.
Published: (2024)

MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
by: Zhang, Yin, et al.
Published: (2026)

EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models
by: Bazarbachi, Omar, et al.
Published: (2025)

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
by: Huang, Yuqing, et al.
Published: (2024)

Pre-training Distillation for Large Language Models: A Design Space Exploration
by: Peng, Hao, et al.
Published: (2024)

EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models
by: Tan, Zheyue, et al.
Published: (2025)