RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
cs.CL
Submitted: 2026-05-25
Updated: 2026-11-17
Terminology
Sources
- Group-in-Group Policy Optimization for LLM Agent Training
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
- GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health
- EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
- NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval
- Tree Search for LLM Agent Reinforcement Learning
- DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- ThinkQE: Query Expansion via an Evolving Thinking Process
- DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
- ConvGQR: Generative Query Reformulation for Conversational Search
- Document Expansion by Query Prediction
- TongSearch-QR: Reinforced Query Reasoning for Retrieval
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- Query2doc: Query Expansion with Large Language Models
- Rank1: Test-Time Compute for Reranking in Information Retrieval
- SmartSearch: Process Reward-Guided Query Refinement for Search Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data