Copertina

How Can LLM Guide RL? A Value-Based Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Shenao, Zheng, Sirui, Ke, Shuqi, Liu, Zhihan, Jin, Wanxin, Yuan, Jianbo, Yang, Yingxiang, Yang, Hongxia, Wang, Zhaoran
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs
di: Liu, Zhihan, et al.
Pubblicazione: (2024)

Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
di: Liu, Zhihan, et al.
Pubblicazione: (2023)

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
di: Liu, Zhihan, et al.
Pubblicazione: (2024)

Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
di: Yang, Yuxiao, et al.
Pubblicazione: (2024)

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
di: Zhang, Shenao, et al.
Pubblicazione: (2024)

Can Large Language Models Play Games? A Case Study of A Self-Play Approach
di: Guo, Hongyi, et al.
Pubblicazione: (2024)

Let Models Speak Ciphers: Multiagent Debate through Embeddings
di: Pham, Chau, et al.
Pubblicazione: (2023)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
di: Zhang, Shenao, et al.
Pubblicazione: (2025)

Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videos
di: Mahesheka, Harsh, et al.
Pubblicazione: (2024)

Learning to Reason as Action Abstractions with Scalable Mid-Training RL
di: Zhang, Shenao, et al.
Pubblicazione: (2025)

Value-Based Pre-Training with Downstream Feedback
di: Ke, Shuqi, et al.
Pubblicazione: (2026)

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
di: Zhang, Shenao, et al.
Pubblicazione: (2024)

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
di: Liu, Zhihan, et al.
Pubblicazione: (2026)

Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?
di: Chen, Wanyi, et al.
Pubblicazione: (2026)

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
di: Zhong, Han, et al.
Pubblicazione: (2025)

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

$\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model
di: Zhang, Yufeng, et al.
Pubblicazione: (2024)

FASTER: Value-Guided Sampling for Fast RL
di: Dong, Perry, et al.
Pubblicazione: (2026)

Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization
di: Xu, Ruijie, et al.
Pubblicazione: (2024)

Toward Optimal LLM Alignments Using Two-Player Games
di: Zheng, Rui, et al.
Pubblicazione: (2024)

Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
di: Zhu, Jianbo, et al.
Pubblicazione: (2026)

DavIR: Data Selection via Implicit Reward for Large Language Models
di: Zhou, Haotian, et al.
Pubblicazione: (2023)

Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach
di: Yang, Xu, et al.
Pubblicazione: (2026)

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
di: Zheng, Haizhong, et al.
Pubblicazione: (2025)

Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias
di: Wu, Sirui, et al.
Pubblicazione: (2025)

ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
di: Yuan, Zhuowen, et al.
Pubblicazione: (2025)

FormaRL: Enhancing Autoformalization with no Labeled Data
di: Huang, Yanxing, et al.
Pubblicazione: (2025)

How Much Can RAG Help the Reasoning of LLM?
di: Liu, Jingyu, et al.
Pubblicazione: (2024)

Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
di: Chen, Wenhao, et al.
Pubblicazione: (2026)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
di: Wu, Junchao, et al.
Pubblicazione: (2024)

Human-Instruction-Free LLM Self-Alignment with Limited Samples
di: Guo, Hongyi, et al.
Pubblicazione: (2024)

SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
di: Cao, Shiyi, et al.
Pubblicazione: (2025)

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
di: Gu, Hao, et al.
Pubblicazione: (2026)

Model Merging Scaling Laws in Large Language Models
di: Wang, Yuanyi, et al.
Pubblicazione: (2025)

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
di: Li, Ang, et al.
Pubblicazione: (2025)

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
di: Zhang, Hao, et al.
Pubblicazione: (2026)

BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data
di: Wang, Xuwu, et al.
Pubblicazione: (2024)

Canonical Intermediate Representation for LLM-based optimization problem formulation and code generation
di: Lyu, Zhongyuan, et al.
Pubblicazione: (2026)

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
di: Tan, Zhewen, et al.
Pubblicazione: (2026)

Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
di: Xin, Ran, et al.
Pubblicazione: (2025)