Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents

• URL: http://arxiv.org/abs/2510.14438v1
• Date: Thu, 16 Oct 2025 08:37:42 GMT
• Title: Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents
• Authors: Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, Kam-Fai Wong,
• Abstract summary: Deep research web agents need to rigorously analyze and aggregate knowledge for insightful research.<n>We propose an Explore to Evolve paradigm to scalably construct verifiable training data for web agents.<n>Based on an open-source agent framework, SmolAgents, we collect supervised fine-tuning trajectories to develop a series of foundation models.
• Score: 70.77400371166922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep research web agents not only retrieve information from diverse sources such as web environments, files, and multimodal inputs, but more importantly, they need to rigorously analyze and aggregate knowledge for insightful research. However, existing open-source deep research agents predominantly focus on enhancing information-seeking capabilities of web agents to locate specific information, while overlooking the essential need for information aggregation, which would limit their ability to support in-depth research. We propose an Explore to Evolve paradigm to scalably construct verifiable training data for web agents. Begins with proactive online exploration, an agent sources grounded information by exploring the real web. Using the collected evidence, the agent then self-evolves an aggregation program by selecting, composing, and refining operations from 12 high-level logical types to synthesize a verifiable QA pair. This evolution from high-level guidance to concrete operations allowed us to scalably produce WebAggregatorQA, a dataset of 10K samples across 50K websites and 11 domains. Based on an open-source agent framework, SmolAgents, we collect supervised fine-tuning trajectories to develop a series of foundation models, WebAggregator. WebAggregator-8B matches the performance of GPT-4.1, while the 32B variant surpasses GPT-4.1 by more than 10% on GAIA-text and closely approaches Claude-3.7-sonnet. Moreover, given the limited availability of benchmarks that evaluate web agents' information aggregation abilities, we construct a human-annotated evaluation split of WebAggregatorQA as a challenging test set. On this benchmark, Claude-3.7-sonnet only achieves 28%, and GPT-4.1 scores 25.8%. Even when agents manage to retrieve all references, they still struggle on WebAggregatorQA, highlighting the need to strengthen the information aggregation capabilities of web agent foundations.

Related papers

• 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)
• InfoAgent: Advancing Autonomous Information-Seeking Agents [143.15973604285304]
  We introduce InfoAgent, a deep research agent powered by an innovative data synthesis pipeline and orchestrated web search tools.<n>With our methods, InfoAgent achieves 15.3% accuracy on BrowseComp, 29.2% on BrowseComp-ZH, and 40.4% on Xbench-DS.
  arXiv  Detail & Related papers  (2025-09-29T17:59:57Z)
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents [57.203515352080295]
  We introduce WebExplorer: a systematic data generation approach using model-based exploration and iterative, long-to-short query evolution.<n>Our model supports 128K context length and up to 100 tool calling turns, enabling long-horizon problem solving.<n>As an 8B-sized model, WebExplorer-8B is able to effectively search over an average of 16 turns after RL training.
  arXiv  Detail & Related papers  (2025-09-08T10:07:03Z)
• 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)
• WebDancer: Towards Autonomous Information Seeking Agency [69.33360019344083]
  Recent progress in agentic systems underscores the potential for autonomous multi-step research.<n>We present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective.<n>We instantiate this framework in a web agent based on the ReAct, WebDancer.
  arXiv  Detail & Related papers  (2025-05-28T17:57:07Z)

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.