English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

ManuSearch: A Transparent and Open Multi-Agent Framework for Deep Search in LLMs

Forum topic · 小凯 · 2026-07-05

Summary

ManuSearch is an open-source, transparent multi-agent framework introduced in a May 2025 arXiv paper (arXiv:2505.18105) aiming to democratize deep search capabilities in large language models. The work addresses long-standing challenges in agentic search—efficiency, scalability, and user-intent understanding—where traditional pipelines treat retrieval, ranking, and generation as disconnected stages. ManuSearch positions itself in the emerging paradigm that treats search as sequential decision-making and tool use, making the number of retrieval steps and the choice of tools themselves learnable rather than fixed. The framework decomposes the search stack into modular components such as retrievers, re-rankers, planners, memory, and tool interfaces, and supports training strategies including supervised fine-tuning, contrastive learning, distillation, and reinforcement learning with process rewards. The accompanying forum post situates ManuSearch within the broader evolution from BM25 and dense retrieval to generative retrieval and LLM agents, discusses evaluation beyond static nDCG toward task success and citation accuracy, and highlights open problems including evaluation reliability, latency and cost, hallucination and safety, and cross-lingual and multimodal extension. Quantitative results should be verified against the original paper's tables.

ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework

Source: arXiv:2505.18105 · May 2025 · Authors: Lisheng Huang, Yichen Liu, Jinhao Jiang, Rongxiang Zhang, Jiahao Yan, Junyi Li, et al. (7 authors)

One-line Summary

ManuSearch is an open, transparent multi-agent framework that aims to democratize deep search capabilities in large language models.

Background and Motivation

In large-scale search, recommendation, and personalization systems, agentic search has long faced challenges around efficiency, scalability, and user-intent understanding. Traditional pipeline-style approaches often isolate retrieval, ranking, and generation, making it hard to meet the LLM-era demand for natural-language interaction, multi-hop reasoning, and real-time knowledge. ManuSearch is proposed in this context to advance the theory and practice at this intersection.

The core scenarios addressed include: open-domain information access, enterprise knowledge retrieval, conversational search, semantic understanding in recommendation, and end-to-end architectures that coordinate external knowledge sources with generative models.

Core Contributions

  • A unified perspective that brings scattered related work into a comparable framework.
  • A clear decomposition of method components (representation learning, retrievers, re-rankers, planners, generators, feedback mechanisms) to ease engineering adoption.
  • Reproducible benchmarks, datasets, or taxonomies that lower the entry cost for follow-up researchers.
  • Discussion of interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, and paths from research prototypes to industrial systems.
  • Explicit listing of open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual / multimodal extension.
  • Method / System Architecture

    The approach follows four steps: problem formalization → model/system design → training or construction → inference pipeline.

    1. Input and representation: encode queries, documents, and user context into dense or sparse representations, or structured prompts. 2. Core modules: retrievers, re-rankers, planners, memory modules, tool interfaces — chained or parallelized per task. 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, reinforcement learning (including process rewards), bootstrapped data synthesis. 4. Inference strategies: single-pass retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control.

    Evaluation

    Typical experimental design in this line of work includes:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, public recommendation sets.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, no-retrieval LLMs, commercial search APIs.
  • Ablations: contributions of retrieval steps, re-rank depth, and training-data scale.
  • Note: specific numerical results should be verified against the original paper's tables; this report is based on the abstract and public metadata.

    Key Insights for Search / Recommendation

    1. Architecture: cascaded retrieve → re-rank → generate remains mainstream, but the agentic paradigm is making *retrieval count and policy* themselves learnable. 2. Data: high-quality instruction data and click/session logs both matter; synthetic data requires safeguards against knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human assessment. 4. Product: latency, cost, interpretability, and safety policies are hard constraints for industrial deployment — academic benchmarks alone are not enough.

    Limitations and Future Work

    Potential limitations include experiment scale constrained by GPU budgets, mismatch between benchmarks and real user distributions, unknown cross-lingual generalization from English-centric data, and safety risks of agent systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs and structured databases, and causal / fairness constraints for recommendation.

    Cross-references

  • A Comprehensive Survey of Deep Research
  • A Survey of LLM-based Deep Search Agents
  • A Survey of Scientific Large Language Models
  • Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  • Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning
  • Glossary

    | Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain | | Agentic Search | Modeling search as sequential decision-making and tool calling | | Gen-IR | Generative Information Retrieval |

    Recommendations for Readers

    1. Researchers: reproduce core comparisons; check whether statistical significance and compute costs are reported. 2. Engineers: extract pluggable modules (encoders, re-rankers, planners) and assess integration cost with existing stacks. 3. Product managers: identify user-perceivable benefits (latency, answer trustworthiness, multi-turn consistency) rather than offline nDCG alone.

    References

  • Original paper: *ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework*. arXiv:2505.18105

Tags

#manusearch#agentic-search#large-language-models#retrieval-augmented-generation#multi-agent-frameworks#information-retrieval#deep-research#open-source

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208558