Buchumschlag

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ren, Qingyu, He, Qianyu, Zhang, Bowei, Zeng, Jie, Liang, Jiaqing, Xiao, Yanghua, Zhou, Weikang, Sun, Zeye, Yu, Fei
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
von: Ren, Qingyu, et al.
Veröffentlicht: (2025)

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following
von: Zeng, Jie, et al.
Veröffentlicht: (2025)

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
von: Ren, Qingyu, et al.
Veröffentlicht: (2025)

SEIF: Self-Evolving Reinforcement Learning for Instruction Following
von: Ren, Qingyu, et al.
Veröffentlicht: (2026)

Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
von: He, Qianxi, et al.
Veröffentlicht: (2025)

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
von: He, Qianyu, et al.
Veröffentlicht: (2024)

LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
von: Ren, Qingyu, et al.
Veröffentlicht: (2026)

Small Language Model Can Self-correct
von: Han, Haixia, et al.
Veröffentlicht: (2024)

Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
von: Huang, Yuncheng, et al.
Veröffentlicht: (2024)

What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty
von: Zhang, Bowei, et al.
Veröffentlicht: (2025)

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
von: Han, Jinyi, et al.
Veröffentlicht: (2025)

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception
von: Huang, Yuncheng, et al.
Veröffentlicht: (2023)

Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases
von: Huang, Wenhao, et al.
Veröffentlicht: (2024)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
von: Han, Jinyi, et al.
Veröffentlicht: (2025)

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
von: Li, Yanda, et al.
Veröffentlicht: (2024)

QUILL: Quotation Generation Enhancement of Large Language Models
von: Xiao, Jin, et al.
Veröffentlicht: (2024)

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models
von: Zhang, Yikai, et al.
Veröffentlicht: (2024)

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
von: Xia, Sirui, et al.
Veröffentlicht: (2024)

Adaptive Ordered Information Extraction with Deep Reinforcement Learning
von: Huang, Wenhao, et al.
Veröffentlicht: (2023)

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base
von: Yuan, Siyu, et al.
Veröffentlicht: (2023)

Can Large Language Models Understand Real-World Complex Instructions?
von: He, Qianyu, et al.
Veröffentlicht: (2023)

ChemHTS: Hierarchical Tool Stacking for Enhancing Chemical Agents
von: Li, Zhucong, et al.
Veröffentlicht: (2025)

When Agents Evolve, Institutions Follow
von: Fei, Chao, et al.
Veröffentlicht: (2026)

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
von: Cai, Shaofei, et al.
Veröffentlicht: (2024)

MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
von: Li, Nianqi, et al.
Veröffentlicht: (2024)

RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following
von: Pan, Tianjun, et al.
Veröffentlicht: (2026)

Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
von: Zhang, Yifei, et al.
Veröffentlicht: (2024)

Structured Reasoning for Large Language Models
von: Han, Jinyi, et al.
Veröffentlicht: (2026)

CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes
von: Zhao, Haokun, et al.
Veröffentlicht: (2024)

Constrained Minimizers of the Fourth‐Order Schrödinger Equation With Saturable Nonlinearity
von: Zeye Han
Veröffentlicht: (2025)

Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction
von: Ding, Zepeng, et al.
Veröffentlicht: (2024)

Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
von: Jiang, Zishang, et al.
Veröffentlicht: (2025)

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment
von: Jiang, Sihang, et al.
Veröffentlicht: (2026)

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
von: He, Qianxi, et al.
Veröffentlicht: (2025)

MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure
von: Kang, Jiale, et al.
Veröffentlicht: (2024)

RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following
von: Wang, Zhichao, et al.
Veröffentlicht: (2025)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
von: Wang, Chenyang, et al.
Veröffentlicht: (2025)

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
von: Sun, Wangtao, et al.
Veröffentlicht: (2024)

Can Pre-trained Language Models Understand Chinese Humor?
von: Chen, Yuyan, et al.
Veröffentlicht: (2024)

BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation
von: Ran, Yiting, et al.
Veröffentlicht: (2025)