Image de couverture de livre

One-Way Policy Optimization for Self-Evolving LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Shuo, Lu, Jinda, Huang, Kexin, Ma, Chiyu, Wei, Shaohang, Liu, Yuyang, Wang, Guoyin, Zhou, Jingren, Yuan, Li
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
par: Meng, Haoming, et autres
Publié: (2026)

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
par: Ma, Chiyu, et autres
Publié: (2026)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
par: Huang, Kexin, et autres
Publié: (2026)

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
par: Zhou, Huilin, et autres
Publié: (2026)

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
par: Yang, Shuo, et autres
Publié: (2026)

NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation
par: Liu, Maoqi, et autres
Publié: (2025)

Self-Evolved Reward Learning for LLMs
par: Huang, Chenghua, et autres
Publié: (2024)

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
par: Zhang, Wenhao, et autres
Publié: (2025)

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
par: Song, Feifan, et autres
Publié: (2025)

Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning
par: Guan, Xin, et autres
Publié: (2026)

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
par: Feng, Xinshun, et autres
Publié: (2026)

PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
par: Lv, Mingrui, et autres
Publié: (2025)

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
par: Chai, Ziwei, et autres
Publié: (2024)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
par: Li, Yibo, et autres
Publié: (2026)

R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning
par: Liu, Jinda, et autres
Publié: (2025)

Self-Evolving LLMs via Continual Instruction Tuning
par: Kang, Jiazheng, et autres
Publié: (2025)

Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation
par: Sui, Yuan, et autres
Publié: (2026)

Soft Adaptive Policy Optimization
par: Gao, Chang, et autres
Publié: (2025)

DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization
par: Tao, Tao, et autres
Publié: (2025)

Unified Parameter-Efficient Unlearning for LLMs
par: Ding, Chenlu, et autres
Publié: (2024)

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning
par: Yang, Wei, et autres
Publié: (2026)

Policy Gradient for Robust Markov Decision Processes
par: Wang, Qiuhao, et autres
Publié: (2024)

Distilling Text Style Transfer With Self-Explanation From LLMs
par: Zhang, Chiyu, et autres
Publié: (2024)

Group Sequence Policy Optimization
par: Zheng, Chujie, et autres
Publié: (2025)

Industrial Surface Defect Detection via Diffusion Generation and Asymmetric Student-Teacher Network
par: Feng, Shuo, et autres
Publié: (2026)

AgentEvolver: Towards Efficient Self-Evolving Agent System
par: Zhai, Yunpeng, et autres
Publié: (2025)

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
par: Huang, Yixu, et autres
Publié: (2026)

Guided Self-Evolving LLMs with Minimal Human Supervision
par: Yu, Wenhao, et autres
Publié: (2025)

LLMs for High-Frequency Decision-Making: Normalized Action Reward-Guided Consistency Policy Optimization
par: Zhao, Yang, et autres
Publié: (2026)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
par: Yang, Xianglin, et autres
Publié: (2026)

Align, Don't Divide: Revisiting the LoRA Architecture in Multi-Task Learning
par: Liu, Jinda, et autres
Publié: (2025)

SkillOpt: Executive Strategy for Self-Evolving Agent Skills
par: Yang, Yifan, et autres
Publié: (2026)

CODESKILL: Learning Self-Evolving Skills for Coding Agents
par: Li, Yanzhou, et autres
Publié: (2026)

MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation
par: He, Junlin, et autres
Publié: (2026)

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
par: Zhang, Wenqi, et autres
Publié: (2024)

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
par: Fan, Zhiyuan, et autres
Publié: (2026)

Position: Agentic Evolution is the Path to Evolving LLMs
par: Lin, Minhua, et autres
Publié: (2026)

SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
par: Li, Chenyi, et autres
Publié: (2026)

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph
par: Zhang, Yutong, et autres
Publié: (2024)

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
par: Liu, Xingyu, et autres
Publié: (2024)