Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

• URL: http://arxiv.org/abs/2509.24107v1
• Date: Sun, 28 Sep 2025 22:58:11 GMT
• Title: Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
• Abstract summary: We introduce Fathom-DeepResearch, an agentic system composed of two specialized models.<n>The first is Fathom-Search-4B, a DeepSearch model optimized for evidence-based investigation through live web search and targeted webpage querying.<n>The second is Fathom- Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports.
• Score: 7.3517692707289415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tool-integrated reasoning has emerged as a key focus for enabling agentic applications. Among these, DeepResearch Agents have gained significant attention for their strong performance on complex, open-ended information-seeking tasks. We introduce Fathom-DeepResearch, an agentic system composed of two specialized models. The first is Fathom-Search-4B, a DeepSearch model trained from Qwen3-4B and optimized for evidence-based investigation through live web search and targeted webpage querying. Its training combines three advances: (i) DUETQA, a 5K-sample dataset generated via multi-agent self-play that enforces strict web-search dependence and heterogeneous source grounding; (ii) RAPO, a zero-overhead extension of GRPO that stabilizes multi-turn Reinforcement Learning with Verifiable Rewards through curriculum pruning, reward-aware advantage scaling, and per-prompt replay buffers; and (iii) a steerable step-level reward that classifies each tool call by cognitive behavior and marginal utility, enabling explicit control over search trajectory breadth, depth, and horizon. These improvements enable reliable extension of tool-calling beyond 20 calls when warranted. The second is Fathom-Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports for comprehensive synthesis. Evaluated on DeepSearch benchmarks (SimpleQA, FRAMES, WebWalker, Seal0, MuSiQue) and DeepResearch-Bench, the system achieves state-of-the-art performance in the open-weights category while demonstrating strong generalization to diverse reasoning tasks including HLE, AIME-25, GPQA-Diamond, and MedQA.

Related papers

• SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation [26.8807904319691]
  We present textbfSearchEyes, which uses a typed knowledge graph as the backbone of a emphsimulated search world<n>We propose textbfPerception-Knowledge Chains (PKC) to sample constrained multi-hop paths over the visual-knowledge intersection of Wikidata5M.<n>Experiments on six multimodal knowledge-intensive benchmarks show that SearchEyes achieves state-of-the-art performance among open-source multimodal search agents.
  arXiv  Detail & Related papers  (2026-07-07T07:43:04Z)
• DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning [58.09293442211248]
  Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks.<n>This report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry.
  arXiv  Detail & Related papers  (2026-06-05T14:10:48Z)
• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents [50.79529228477821]
  We introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning.<n>First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding.<n>Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction.
  arXiv  Detail & Related papers  (2026-05-06T17:50:38Z)
• EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools [12.61248869302151]
  We introduce Q+, a set of query and evidence processing tools that make web search more deliberate.<n>We integrate Q+ into the browser sub-agent of Eigent, an open-source, production-ready multi-agent workforce.<n>Across four benchmarks, Q+ improves Eigent's browser agent benchmark-size-weighted average accuracy by 3.0, 3.8, and 0.6 percentage points (pp)
  arXiv  Detail & Related papers  (2026-04-09T07:47:31Z)
• Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design [39.31356016375221]
  Marco DeepResearch is a deep research agent optimized with a verification-centric framework design at three levels.<n>We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty.<n>We design a verification-driven synthesis trajectory method that injects explicit verification patterns into training trajectories.<n>We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions.
  arXiv  Detail & Related papers  (2026-03-30T12:42:02Z)
• AgentIR: Reasoning-Aware Retrieval for Deep Research Agents [76.29382561831105]
  Deep Research agents generate explicit natural language reasoning before each search call.<n> Reasoning-Aware Retrieval embeds the agent's reasoning trace alongside its query.<n>DR- Synth generates Deep Research retriever training data from standard QA datasets.<n>AgentIR-4B achieves 68% accuracy with the open-weight agent Tongyi-DeepResearch.
  arXiv  Detail & Related papers  (2026-03-04T18:47:26Z)
• DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent [63.52637950356965]
  DeepResearch-9K is a large-scale, challenging dataset for deep-research scenarios.<n>DeepResearch-R1 is an open-source training framework for deep-research agents.
  arXiv  Detail & Related papers  (2026-03-01T15:36:10Z)
• MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline [26.19213349415094]
  We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis.<n>We observe three main challenges in developing such agents: (1) scarcity of search-intensive multimodal QA data, (2) lack of effective search trajectories, and (3) prohibitive cost of training with online search APIs.<n>With the three designs, we develop MM-DeepResearch, a powerful multimodal deep research agent, and extensive results shows its superiority across benchmarks.
  arXiv  Detail & Related papers  (2026-03-01T11:13:22Z)
• DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL [60.47878242100153]
  We present DeepDive to advance deep search agents.<n>We propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs.<n>Experiments show that DeepDive-32B achieves a new open-source competitive result on BrowseComp.
  arXiv  Detail & Related papers  (2025-09-12T17:52:35Z)
• Open Data Synthesis For Deep Research [17.22470203913576]
  We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems.<n>Existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity.<n>We introduce InfoSeek, a scalable scalable complex Deep Research tasks.
  arXiv  Detail & Related papers  (2025-08-30T06:02:56Z)
• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent [74.10138164281618]
  BrowseComp-Plus is a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus.<n>This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods.
  arXiv  Detail & Related papers  (2025-08-08T17:55:11Z)
• MMSearch-R1: Incentivizing LMMs to Search [49.889749277236376]
  We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables on-demand, multi-turn search in real-world Internet environments.<n>Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty.
  arXiv  Detail & Related papers  (2025-06-25T17:59:42Z)
• From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents [96.65646344634524]
  Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research.<n>We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn.<n>We demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking.
  arXiv  Detail & Related papers  (2025-06-23T17:27:19Z)
• SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis [89.99161034065614]
  Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios.<n>Existing approaches face critical limitations that lack high-quality training trajectories and suffer from distributional mismatches.<n>This paper introduces SimpleDeepSearcher, a framework that bridges the gap through strategic data engineering rather than complex training paradigms.
  arXiv  Detail & Related papers  (2025-05-22T16:05:02Z)
• DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments [20.498100965239818]
  We introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents.<n>Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web.<n>Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines.
  arXiv  Detail & Related papers  (2025-04-04T04:41:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.