Cover Image

Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Jiashu, Huang, Heyan, Luo, Chuwei, Wu, Daiqing, Liu, Zeming, Guo, Yuhang, Kang, Yangyang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
by: Yao, Jiashu, et al.
Published: (2026)

Deterministic Reversible Data Augmentation for Neural Machine Translation
by: Yao, Jiashu, et al.
Published: (2024)

Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
by: Yao, Jiashu, et al.
Published: (2025)

HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection
by: Gao, Siyuan, et al.
Published: (2025)

ReFF: Reinforcing Format Faithfulness in Language Models across Varied Tasks
by: Yao, Jiashu, et al.
Published: (2024)

Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation
by: Qiu, Yuli, et al.
Published: (2024)

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices
by: Li, Silin, et al.
Published: (2025)

DocMEdit: Towards Document-Level Model Editing
by: Zeng, Li, et al.
Published: (2025)

FAME: Towards Factual Multi-Task Model Editing
by: Zeng, Li, et al.
Published: (2024)

DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
by: Wan, Zhongwei, et al.
Published: (2026)

PRIM: Towards Practical In-Image Multilingual Machine Translation
by: Tian, Yanzhi, et al.
Published: (2025)

Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation
by: Tian, Yanzhi, et al.
Published: (2026)

Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
by: Ma, Qinghe, et al.
Published: (2026)

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
by: An, Zihao, et al.
Published: (2026)

Subtopic-aware View Sampling and Temporal Aggregation for Long-form Document Matching
by: Zhou, Youchao, et al.
Published: (2024)

Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
by: Liu, Runheng, et al.
Published: (2026)

Failure Modes of Maximum Entropy RLHF
by: Çağatan, Ömer Veysel, et al.
Published: (2025)

Duality-based Mode Operations and Pyramid Multilayer Mapping for Rhetorical Modes
by: Wu, Zi-Niu
Published: (2025)

Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
by: Yan, Hao, et al.
Published: (2026)

Exploring In-Image Machine Translation with Real-World Background
by: Tian, Yanzhi, et al.
Published: (2025)

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
by: Zhou, Jiang, et al.
Published: (2026)

Mediating Modes of Thought: LLM's for design scripting
by: Rietschel, Moritz, et al.
Published: (2024)

BizFinBench.v2: A Unified Dual-Mode Bilingual Benchmark for Expert-Level Financial Capability Alignment
by: Guo, Xin, et al.
Published: (2026)

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
by: Luo, Chuwei, et al.
Published: (2024)

A Preliminary Exploration with GPT-4o Voice Mode
by: Lin, Yu-Xiang, et al.
Published: (2025)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
by: Fu, Yuqian, et al.
Published: (2026)

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems
by: Kim, Minsoo, et al.
Published: (2025)

How Far Are We? Systematic Evaluation of LLMs vs. Human Experts in Mathematical Contest in Modeling
by: Liu, Yuhang, et al.
Published: (2026)

Training-free Truthfulness Detection via Value Vectors in LLMs
by: Liu, Runheng, et al.
Published: (2025)

LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation
by: Yang, Gao, et al.
Published: (2025)

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
by: Xu, Wujiang, et al.
Published: (2025)

Adaptive Social Learning via Mode Policy Optimization for Language Agents
by: Wang, Minzheng, et al.
Published: (2025)

DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
by: Zhang, Junshuo, et al.
Published: (2026)

ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU
by: Sunesh, Aman, et al.
Published: (2026)

Dual Optimal: Make Your LLM Peer-like with Dignity
by: Wang, Xiangqi, et al.
Published: (2026)

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
by: Cheng, Xiaoxue, et al.
Published: (2025)

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
by: Zhou, Chenxi, et al.
Published: (2026)

SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization
by: Wu, Jianghao, et al.
Published: (2025)

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
by: Liu, Xunzhuo, et al.
Published: (2026)