Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval

arXiv:2507.10057 · cs.IR, cs.AI, cs.CL, cs.LG · Submitted 2025-07-14 · Read on arXiv

cs.IR, cs.AI, cs.CL, cs.LG

Submitted: 2025-07-14

Updated: 2026-10-18

Code: https://github.com/psw0021/Chain-of-Retrieval-Official

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Papers — 4× in this paper · explained in 3 episodes
• Chain of Retrieval — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
• Granite Embedding Models
• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
• MARG: Multi-Agent Review Generation for Scientific Papers
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• The Llama 3 Herd of Models
• Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective
• Reviewer2: Optimizing Review Generation Through Prompt Generation
• PaECTER: Patent-level Representation Learning using Citation-informed Transformers
• Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
• Unsupervised Dense Information Retrieval with Contrastive Learning
• AgentReview: Exploring Peer Review Dynamics with LLM Agents
• MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting
• ScholarEval: Research Idea Evaluation Grounded in Literature
• MTEB: Massive Text Embedding Benchmark
• Document Expansion by Query Prediction
• Contextual Document Similarity for Content-based Literature Recommender Systems

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
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• From a Large-Scale Teacher to Efficient Multimodal Students for Search Relevance Prediction