DiffResearch: Accelerating Deep Research with Diffusion Language Models

DiffResearch, an open multi-agent deep research framework released under the Apache-2.0 license, runs a diffusion language model at every stage and is roughly 6 times faster end-to-end than a comparable autoregressive backbone, according to the arXiv:2610.28909v1 paper. Across 100 Deep Research Bench tasks, holding the agentic scaffold, retrieval code, prompts and evaluation fixed, the diffusion backbone cut planning and writing latency by an order of magnitude, and its dFast decomposition mode, which reads intermediate denoising states to extract subqueries before generation finishes, delivered a 1.99 times median speedup for decomposition in isolation with no loss of report quality. On the benchmark's RACE rubric, dFast scored best overall among the three configurations, and in a public system-level leaderboard snapshot an instance built on a stronger diffusion model ranked above several commercial systems.

arXiv:2610.28909v1 Announce Type: new Abstract: Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on autoregressive AR language models and inherit left-to-right decoding in planning and long-form writing. We present DiffResearch, an open multi-agent deep research framework that places a diffusion language model dLLM at the core of every stage, and measure how a diffusion backbone changes latency and report quality. Holding the agentic scaffold, retrieval code, prompts, and evaluation fixed, we swap the backbone between an open diffusion model and a comparable AR model. Across 100 Deep Research Bench tasks, the diffusion backbone is roughly 6 times faster end-to-end, driven by order-of-magnitude reductions in planning and writing. We further introduce dFast, a decomposition mode that reads intermediate denoising states and extracts subqueries before generation finishes, providing a 1.99 times median speedup for decomposition in isolation with no loss of report quality. On the benchmark's RACE rubric, dFast obtains the best overall score among the three configurations. Finally, in a public system-level leaderboard snapshot, an instance built on a stronger diffusion model ranks above several commercial systems. We release DiffResearch under an Apache-2.0 license.