Deep Researcher with Test-Time Diffusion
read the original abstract
Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration from the iterative nature of human research, which involves cycles of searching, reasoning, and revision, we propose the Test-Time Diffusion Deep Researcher (TTD-DR). This novel framework conceptualizes research report generation as a diffusion process. TTD-DR initiates this process with a preliminary draft, an updatable skeleton that serves as an evolving foundation to guide the research direction. The draft is then iteratively refined through a "denoising" process, which is dynamically informed by a retrieval mechanism that incorporates external information at each step. The core process is further enhanced by a self-evolutionary algorithm applied to each component of the agentic workflow, ensuring the generation of high-quality context for the diffusion process. This draft-centric design makes the report writing process more timely and coherent while reducing information loss during the iterative search process. We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks that require intensive search and multi-hop reasoning, significantly outperforming existing deep research agents.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
AgentDisCo disentangles exploration and exploitation in research agents via critic-generator collaboration and meta-optimization, achieving competitive performance on benchmarks while introducing the GALA benchmark fr...
-
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
AgentDisCo disentangles exploration and exploitation via critic-generator agent pairs and code-agent meta-optimization to generate research reports, matching top systems on benchmarks while introducing the GALA benchm...
-
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
CAP-TTA triggers context-aware preconditioned LoRA updates on high bias-risk OOD prompts to reduce toxicity in LLM narrative generation while preserving fluency and avoiding catastrophic forgetting.
-
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
ScaffoldAgent improves long-form report generation by modeling outline evolution as expansion, contraction, and revision guided by a utility function estimating downstream value.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxo...
-
Evolutionary Profiles for Protein Fitness Prediction
EvoIF integrates within-family and cross-family evolutionary signals into a compact model to achieve competitive or state-of-the-art zero-shot fitness prediction on ProteinGym using only 0.15% of typical training data.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.