Argus: Evidence Assembly for Scalable Deep Research Agents

• URL: http://arxiv.org/abs/2605.16217v3
• Date: Wed, 20 May 2026 01:48:19 GMT
• Title: Argus: Evidence Assembly for Scalable Deep Research Agents
• Abstract summary: We propose a system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces.<n>We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent.<n>With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks.
• Score: 74.04848873346145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which parallel rollouts often duplicate rather than complete, yielding diminishing returns while pushing the aggregation context toward the model's limit. We propose Argus, an agentic system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces, rather than brute forcing the whole answer in parallel. The Searcher collects evidence traces for a given sub-query through ReAct-style interaction. The Navigator maintains a shared evidence graph, verifying which pieces are still missing, dispatching Searchers to gather them, and reasoning over the completed graph to produce a source-traced final answer. We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent. The resulting Navigator supports rollouts with a single Searcher or many in parallel without retraining. With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks. With 64 Searchers it reaches 86.2 on BrowseComp, surpassing every proprietary agent we benchmark, while the Navigator's reasoning context stays under 21.5K tokens.

Related papers

• Iris: Climbing to the Search Frontier [21.066541702697112]
  We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them.
  arXiv  Detail & Related papers  (2026-09-03T17:51:01Z)
• SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task [28.244711705405056]
  Training effective search agents remains challenging due to the lack of scalable and long-horizon tasks.<n>We introduce SearchArt, a framework for training long-horizon search agents.<n>SearchArt constructs large-scale datasets for complex search-, research- and user-oriented tasks.
  arXiv  Detail & Related papers  (2026-07-25T06:47:46Z)
• 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)
• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [74.0621258662676]
  We propose Ptah, a multi-agent harness for interleaved report generation.<n>Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training [28.912613644535668]
  We present PRAISE, a framework for improving data efficiency and credit assignment in agentic search training.<n>Our method uses a single shared model for both search policy learning and prefix answer evaluation.<n>Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.
  arXiv  Detail & Related papers  (2026-04-04T10:23:46Z)
• OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis [63.8655724265611]
  Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning.<n>Existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce.<n>We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis.
  arXiv  Detail & Related papers  (2026-03-17T20:10:12Z)
• Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve) [0.0]
  This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics.<n>Our system utilizes two key innovations: Sequential Research Plan Refinement via Reflection and a Candidates Crossover algorithm.<n>Our architecture achieved an overall score of 46.21, demonstrating superior performance by surpassing leading deep research agents.
  arXiv  Detail & Related papers  (2026-01-28T18:45:39Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• 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>We apply end-to-end multi-turn reinforcement learning to enhance LLMs' long-horizon reasoning with deep search.
  arXiv  Detail & Related papers  (2025-09-12T17:52:35Z)
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning [20.11646932754985]
  Reasoning-augmented search agents such as Search-R1 demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources.<n>Existing approaches suffer from a fundamental architectural limitation: they process search queries strictly sequentially, even when handling inherently parallelizable and logically independent comparisons.<n>We propose ParallelSearch, a novel reinforcement learning framework that empowers large language models to recognize parallelizable query structures and execute multiple search operations concurrently.
  arXiv  Detail & Related papers  (2025-08-12T19:38:21Z)
• 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)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)

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.