Cover Image

Future Policy Approximation for Offline Reinforcement Learning Improves Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oh, Minjae, Choi, Yunho, Choi, Dongmin, Jo, Yohan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

KL for a KL: On-Policy Distillation with Control Variate Baseline
by: Oh, Minjae, et al.
Published: (2026)

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
by: Choi, Yunho, et al.
Published: (2026)

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding
by: Song, Sangjun, et al.
Published: (2025)

Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items
by: Han, Jongwook, et al.
Published: (2025)

PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness Ratings
by: Kim, Junseo, et al.
Published: (2025)

Human Psychometric Questionnaires Mischaracterize LLM Behavior
by: Song, Woojung, et al.
Published: (2025)

Context-Robust Knowledge Editing for Language Models
by: Park, Haewon, et al.
Published: (2025)

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
by: Chae, Kyubyung, et al.
Published: (2024)

ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation
by: Kim, Jiho, et al.
Published: (2025)

Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap
by: Ko, Hyunwoo, et al.
Published: (2025)

R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs
by: Jo, Sumin, et al.
Published: (2025)

Model-based Preference Optimization in Abstractive Summarization without Human Feedback
by: Choi, Jaepill, et al.
Published: (2024)

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples
by: Pyun, Haesung, et al.
Published: (2025)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
by: Wang, Huaijie, et al.
Published: (2024)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
by: Lee, Yohan, et al.
Published: (2026)

Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning
by: Mu, Yongyu, et al.
Published: (2026)

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
by: Park, Yoonah, et al.
Published: (2025)

SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings
by: Park, Haewon, et al.
Published: (2025)

Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers
by: Heo, Chaewon, et al.
Published: (2026)

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
by: Zhan, Shaoxiong, et al.
Published: (2025)

Improving Multi-lingual Alignment Through Soft Contrastive Learning
by: Park, Minsu, et al.
Published: (2024)

Bridging Offline and Online Reinforcement Learning for LLMs
by: Lanchantin, Jack, et al.
Published: (2025)

PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
by: Lu, Yao, et al.
Published: (2026)

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
by: Wang, Siyuan, et al.
Published: (2024)

ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations
by: Pham, Quang Hieu, et al.
Published: (2025)

Learning to Reason Across Parallel Samples for LLM Reasoning
by: Qi, Jianing, et al.
Published: (2025)

Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning
by: Zhang, Kepu, et al.
Published: (2025)

Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction
by: Park, Sejun, et al.
Published: (2026)

TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning
by: Huang, Xu, et al.
Published: (2026)

EONSim: An NPU Simulator for On-Chip Memory and Embedding Vector Operations
by: Choi, Sangun, et al.
Published: (2025)

Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues
by: Cho, Ye-eun, et al.
Published: (2025)

In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents
by: Lee, Seungkyu, et al.
Published: (2025)

Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
by: Jia, Mengzhao, et al.
Published: (2024)

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
by: Kong, Injin, et al.
Published: (2026)

Thinking Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs
by: Won, Jeongmoon, et al.
Published: (2026)

Extractive text summarisation of Privacy Policy documents using machine learning approaches
by: Choi, Chanwoo
Published: (2024)

Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning
by: Prajapat, Dharmendra, et al.
Published: (2024)

ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
by: Shim, Jeonghoon, et al.
Published: (2025)

SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?
by: Lee, Jonggeun, et al.
Published: (2026)

SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue
by: Lee, Jonggeun, et al.
Published: (2026)