DeepResearch Agent System

• URL: http://arxiv.org/abs/2607.27562v1
• Date: Thu, 30 Jul 2026 01:15:47 GMT
• Title: DeepResearch Agent System
• Abstract summary: DeepResearch Agent System is a large language model system engineered for deep information retrieval, multi-step reasoning, and autonomous research tasks.<n>System supports a 128K-token context window with hierarchical attention mechanisms that yield 18.7% accuracy and 23.4% recall improvements.<n>System is fully open-sourced, including data synthesis, training, and inference code, and supports applications in academic research, business analysis, R&D support, and education.
• Score: 0.919770842662809
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The DeepResearch Agent System is a large language model system engineered for deep information retrieval, multi-step reasoning, and autonomous research tasks. Built upon a sparse activation architecture with 30 billion total parameters of which only 3 billion are activated per token, the system achieves state-of-the-art performance on multiple agent search benchmarks while delivering 3.2 times faster inference compared to dense counterparts of equivalent scale. The system supports a 128K-token context window with hierarchical attention mechanisms that yield 18.7% accuracy and 23.4% recall improvements over standard long-context approaches. A dual-mode reasoning engine provides both a ReAct paradigm for basic multi-step problem solving and an IterResearch mode for high-performance iterative research with up to 20 reasoning steps, collectively delivering a 31.2% accuracy improvement over single-pass baselines. Multi-tool coordination integrates retrieval, computation, web search, and file parsing modules to achieve 92.1% tool-use accuracy. A reinforcement learning optimization framework based on the GRPO algorithm provides token-level policy gradients that improve training stability by 35% and accelerate convergence by 42%. An automated data synthesis pipeline with seed-based expansion achieves a 92.5% usability rate. Benchmark results include 87.3% on Humanity's Last Exam, 85.3% on BrowserComp Chinese, and 91.2% on WebWalkerQA. The system is fully open-sourced, including data synthesis, training, and inference code, and supports applications in academic research, business analysis, R&D support, and education.

Related papers

• A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation [0.0]
  This paper proposes a multi-agent framework built on CrewAI for conversational business intelligence.<n>Five specialized AI agents operate in a sequential pipeline to process natural language queries, retrieve and analyze data, generate visualizations, and deliver actionable insights.
  arXiv  Detail & Related papers  (2026-08-19T09:49:58Z)
• optimize_anything: A Universal API for Optimizing any Text Parameter [98.42497715725356]
  We show a single AI-based optimization system-supporting single-task search, multi-task search with cross-problem transfer, and generalization to unseen inputs.<n>We show for the first time that text optimization with LLM-based search is a general-purpose problem-solving paradigm.
  arXiv  Detail & Related papers  (2026-05-19T10:18:12Z)
• Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU [0.15293427903448018]
  Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency.<n>This paper proposes Adaptive Tree-of-Retrieval (Adaptive ToR), a complexity-aware retrieval architecture that dynamically configures retrieval topology based on query characteristics.
  arXiv  Detail & Related papers  (2026-04-27T09:24:10Z)
• From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents [51.12380889298618]
  POISE is a framework for automated discovery of policy optimization algorithms for language models.<n>PoISE maintains a structured, genealogically linked archive linking proposals, executable implementations, standardized evaluations, and natural-language reflections.
  arXiv  Detail & Related papers  (2026-03-25T05:19:23Z)
• PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models [5.598141218271656]
  Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited.<n>We propose PRIME, a framework comprising three specialized agents, an executor for step-by-step reasoning, a verifier for constraint checking, and a coordinator for backtracking control.<n>For comprehensive evaluation, we introduce PRIME-Bench, the largest algorithmic reasoning benchmark to date, comprising 86 tasks across 12 categories with 51,600 instances.
  arXiv  Detail & Related papers  (2026-01-19T07:57:01Z)
• ROAD: Reflective Optimization via Automated Debugging for Zero-Shot Agent Alignment [1.6968020497268546]
  ROAD is a novel framework that treats optimization as a dynamic debug investigation rather than a search.<n>Road is highly sample-efficient, achieving a 5.6 percent increase in success rate and a 3.8 percent increase in search accuracy.<n>These findings suggest that mimicking the human engineering loop of failure analysis and patching offers a viable, data-efficient alternative to resource-intensive training.
  arXiv  Detail & Related papers  (2025-12-30T07:31:34Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training [0.0]
  This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification.<n>We achieve 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models.<n>Our approach achieves performance within 1.34% of fine-tuned ResNet-50 (98.57%) while requiring no external data.
  arXiv  Detail & Related papers  (2025-10-17T10:59:24Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Advanced Multi-Architecture Deep Learning Framework for BIRADS-Based Mammographic Image Retrieval: Comprehensive Performance Analysis with Super-Ensemble Optimization [0.0]
  mammographic image retrieval systems require exact BIRADS categorical matching across five distinct classes.<n>Current medical image retrieval studies suffer from methodological limitations.
  arXiv  Detail & Related papers  (2025-08-06T18:05:18Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• Tactile Grasp Refinement using Deep Reinforcement Learning and Analytic Grasp Stability Metrics [70.65363356763598]
  We show that analytic grasp stability metrics constitute powerful optimization objectives for reinforcement learning algorithms. We show that a combination of geometric and force-agnostic grasp stability metrics yields the highest average success rates of 95.4% for cuboids. In a second experiment, we show that grasp refinement algorithms trained with contact feedback perform up to 6.6% better than a baseline that receives no tactile information.
  arXiv  Detail & Related papers  (2021-09-23T09:20:19Z)

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.