Cover Image

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Chengjun, Liu, Shichun, Lin, Jiahang, Zhu, Dingwei, Zhang, Jiazheng, Dou, Shihan, Gao, Songyang, Han, Zhenhua, Wang, Binghai, Zheng, Rui, Huang, Xuanjing, Gui, Tao, Feng, Yansong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
by: Lin, Jiahang, et al.
Published: (2026)

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2025)

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
by: Lin, Jiahang, et al.
Published: (2026)

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2026)

Improving RL Exploration for LLM Reasoning through Retrospective Replay
by: Dou, Shihan, et al.
Published: (2025)

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
by: Ding, Deming, et al.
Published: (2026)

Pre-Trained Policy Discriminators are General Reward Models
by: Dou, Shihan, et al.
Published: (2025)

RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
by: Zhou, Enyu, et al.
Published: (2024)

Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization
by: Liu, Boyang, et al.
Published: (2025)

JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees
by: Wang, Yuhui, et al.
Published: (2026)

VRPO: Rethinking Value Modeling for Robust RL Training under Noisy Supervision
by: Zhu, Dingwei, et al.
Published: (2025)

Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion
by: Zang, Jianxiang, et al.
Published: (2025)

Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
by: Zhang, Jiazheng, et al.
Published: (2026)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
by: Wang, Junzhe, et al.
Published: (2026)

ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
by: Ye, Junjie, et al.
Published: (2024)

Can RL Improve Generalization of LLM Agents? An Empirical Study
by: Xi, Zhiheng, et al.
Published: (2026)

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
by: Zhang, Ming, et al.
Published: (2024)

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
by: Zhang, Kaichen, et al.
Published: (2025)

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
by: Wang, Yuanyi, et al.
Published: (2026)

Following the TRAIL: Predicting and Explaining Tomorrow's Hits with a Fine-Tuned LLM
by: Zhang, Yinan, et al.
Published: (2026)

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
by: Zhang, Jiazheng, et al.
Published: (2025)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2024)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
by: Xi, Zhiheng, et al.
Published: (2023)

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
by: Lv, Huijie, et al.
Published: (2024)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
by: Zhang, Hongyin, et al.
Published: (2025)

Forecasts of CMB $E$-mode anomalies for AliCPT-1
by: Dou, Jiazheng, et al.
Published: (2026)

Forecasts of constraining isotropic cosmic birefringence on AliCPT-1
by: Dou, Jiazheng, et al.
Published: (2025)

LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
by: Dou, Shihan, et al.
Published: (2023)

Prefix-Adaptive Block Diffusion for Efficient Document Recognition
by: Chai, Mingxu, et al.
Published: (2026)

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
by: Fakoor, Rasool, et al.
Published: (2026)

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation
by: Zhang, Ming, et al.
Published: (2025)

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
by: Shen, Yujiong, et al.
Published: (2026)

Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
by: Xu, Nuo, et al.
Published: (2024)

Steering LLMs via Scalable Interactive Oversight
by: Zhou, Enyu, et al.
Published: (2026)

MetaRM: Shifted Distributions Alignment via Meta-Learning
by: Dou, Shihan, et al.
Published: (2024)

Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning
by: Zhu, Changxi, et al.
Published: (2025)

Near-Ultimate Quantum-Enhanced Sensitivity in Dissipative Critical Sensing with Partial Access
by: Zhao, Dingwei, et al.
Published: (2025)

Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design
by: Eshuijs, Leon, et al.
Published: (2026)

Tight Competitive and Variance Analyses of Matching Policies in Gig Platforms
by: Xu, Pan
Published: (2024)

AgentV-RL: Scaling Reward Modeling with Agentic Verifier
by: Zhang, Jiazheng, et al.
Published: (2026)