Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Guoqing, Dai, Sunhao, Ye, Guangze, Gan, Zeyu, Yao, Wei, Deng, Yong, Wu, Xiaofeng, Ying, Zhenzhe
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
di: Venus Team, et al.
Pubblicazione: (2026)

Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
di: Deng, Yong, et al.
Pubblicazione: (2025)

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

MARPO: A Reflective Policy Optimization for Multi Agent Reinforcement Learning
di: Wu, Cuiling, et al.
Pubblicazione: (2025)

RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking
di: Yang, Shuo, et al.
Pubblicazione: (2025)

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
di: Dai, Yuqin, et al.
Pubblicazione: (2025)

AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
di: Zong, Zefang, et al.
Pubblicazione: (2026)

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
di: Feng, Mingqian, et al.
Pubblicazione: (2026)

SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo
di: Ma, Zeyu, et al.
Pubblicazione: (2026)

Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs
di: Wei, Chenxing, et al.
Pubblicazione: (2025)

ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue
di: Cao, Ruike, et al.
Pubblicazione: (2026)

SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent
di: Zhong, Wenlin, et al.
Pubblicazione: (2026)

Distributed Consensus Control of Feedforward Nonlinear Time‐Delay Multi‐Agent Systems With Switching Topologies: A Time‐Varying Gain Approach
di: Xiaofeng Xu, et al.
Pubblicazione: (2026)

Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents
di: Song, Yurun, et al.
Pubblicazione: (2026)

GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
di: Zhang, Heng, et al.
Pubblicazione: (2025)

Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent
di: Feng, Xueyang, et al.
Pubblicazione: (2025)

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
di: Kalyan, Vivek, et al.
Pubblicazione: (2025)

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
di: Ding, Yifeng, et al.
Pubblicazione: (2025)

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification
di: Kruse, Maya, et al.
Pubblicazione: (2025)

Disentangled Modeling of Preferences and Social Influence for Group Recommendation
di: Ye, Guangze, et al.
Pubblicazione: (2025)

Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity
di: Su, Zhiyuan, et al.
Pubblicazione: (2025)

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
di: Gan, Zeyu, et al.
Pubblicazione: (2024)

IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
di: Liang, Zihan, et al.
Pubblicazione: (2026)

Direct Multi-Turn Preference Optimization for Language Agents
di: Shi, Wentao, et al.
Pubblicazione: (2024)

RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
di: Zhong, Haitian, et al.
Pubblicazione: (2026)

ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
di: Wang, Zhebo, et al.
Pubblicazione: (2026)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
di: Djuhera, Aladin, et al.
Pubblicazione: (2026)

On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
di: Deng, Wenlong, et al.
Pubblicazione: (2025)

Simple Policy Optimization
di: Xie, Zhengpeng, et al.
Pubblicazione: (2024)

Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
di: Hu, Senkang, et al.
Pubblicazione: (2026)

Length-Induced Embedding Collapse in PLM-based Models
di: Zhou, Yuqi, et al.
Pubblicazione: (2024)

UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems
di: Zhang, Changshuo, et al.
Pubblicazione: (2024)

Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation
di: Wei, Chenxing, et al.
Pubblicazione: (2026)

Learning to Retrieve from Agent Trajectories
di: Zhou, Yuqi, et al.
Pubblicazione: (2026)

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
di: Li, MingSheng, et al.
Pubblicazione: (2025)

NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search
di: Dai, Sunhao, et al.
Pubblicazione: (2025)

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
di: Xie, Yunfei, et al.
Pubblicazione: (2026)

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
di: Dai, Zijie, et al.
Pubblicazione: (2026)

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
di: Wei, Quan, et al.
Pubblicazione: (2025)

FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation
di: Zhang, Chenxi, et al.
Pubblicazione: (2026)