STORM: Stepwise Token Optimization with Reward-Guided Beam Search

arXiv:2606.10621 · cs.IR, cs.AI · Submitted 2026-06-09 · Read on arXiv

cs.IR, cs.AI

Submitted: 2026-06-09

Updated: 2026-08-26

Terminology

• Information Retrieval — 11× in this paper
• Benchmark — 7× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• Pseudo-Relevance Feedback — 2× in this paper
• Pseudo-labels — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation — 2× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• GRPO — 1× in this paper · explained in 6 episodes
• Generative Cooperative Networks — 1× in this paper
• National Institute of Standards and Technology — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes

Sources

• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
• mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
• Unsupervised Dense Information Retrieval with Contrastive Learning
• RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
• Query Expansion by Prompting Large Language Models
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Generative Cooperative Networks for Natural Language Generation
• Qwen3 Technical Report
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
• Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
• Query2doc: Query Expansion with Large Language Models
• Generative Query Reformulation for Effective Adhoc Search
• Passage Re-ranking with BERT

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG