arXiv AI
Jul 1
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
arXiv:2604. 17931v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents.
Open-source DeepResearch – Freeing our search agents
Related stories
arXiv AI
Jun 6
Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation
arXiv:2606. 05241v1 Announce Type: cross Abstract: Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the web during inference.
Hugging Face Trending Papers
Jun 30
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search
We present SimpleSearch-VL, an efficient, reliable, and practical framework for multimodal agentic search. Its core idea is to improve the agent's own search-and-verification process rather than scaling data, tools, or auxiliary model components.
arXiv Computation and Language
Sep 11
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
OpenResearcher is a fully open, reproducible pipeline for generating long‑horizon deep research trajectories that interleave search, evidence aggregation, and multi‑step reasoning. It decouples corpus bootstrapping from trajectory synthesis and runs the search‑and‑browse loop offline using three browser primitives over a 15M‑document corpus. Using GPT‑OSS‑120B as a teacher, the pipeline produced over 97K trajectories, enabling a 30B‑A3B model to achieve 54.8% accuracy on BrowseComp‑Plus and providing insights into pipeline design through controlled analysis.
arXiv Computation and Language
6d ago
Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search
The paper introduces Traverse, an autonomous web‑search agent that manages its search process through three states—Rubric, Answer, and Verify—while using a Seal Memory tool for active context management. Reinforcement learning is employed to train the agent, but a training instability called Seal Collapse is mitigated by training only the final segment after context management. The resulting 35B model achieves state‑of‑the‑art performance on BrowseComp and related benchmarks, outperforming comparable open‑source systems.
arXiv AI
Aug 5
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
arXiv:2608. 03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration.
arXiv AI
Aug 25
From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation
arXiv:2608.23045v1 Announce Type: new Abstract: Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent h...
arXiv Computation and Language
Sep 11
DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports
Deep Research Bench II is a new benchmark designed to evaluate Deep Research Agents (DRAs) by requiring them to produce research reports for 132 grounded tasks across 22 domains. Each report is assessed using 9,430 fine‑grained binary rubrics that cover information recall, analysis, and presentation, all derived from expert‑written investigative articles through a rigorous LLM‑plus‑human pipeline. Evaluation of current state‑of‑the‑art DRAs shows that even the best models satisfy fewer than 50% of these rubrics, highlighting a significant gap between automated agents and human experts.
OpenAI Blog
Feb 2, 2025
Introducing deep research
An agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks for you. Available to Pro users today, Plus and Team next.
arXiv Machine Learning
Aug 12
SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
arXiv:2607. 24850v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons.
arXiv Computation and Language
Sep 3
Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation
The paper introduces a method for creating query‑specific rubrics for DeepResearch‑style long‑form report generation by training rubric generators with reinforcement learning. It builds a dataset of queries annotated with human preferences, then uses a hybrid reward that includes preference consistency, format validity, and LLM‑based rubric evaluation. The learned rubrics outperform generic or manually constructed alternatives in distinguishing preferred reports and, when used as rewards, improve performance of both single‑agent and multi‑agent DeepResearch systems.
arXiv AI
Jun 2
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
arXiv:2606. 00408v1 Announce Type: cross Abstract: Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important.