Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

DeepSearch-Evolve: Self-Distillation Enables Scalable Self-Improvement for Web Agents

AI By Crimson AI Hugging Face Papers 21 July 2026 · 00:00 11 views
Share: X Telegram

Hugging Face introduces DeepSearch-Evolve, a self-distillation framework that trains web agents to improve from their own experience using a deterministic, verifiable environment called DeepSearch-World. The 9B model achieves competitive results without distillation from stronger models.

DeepSearch-Evolve: Self-Distillation Enables Scalable Self-Improvement for Web Agents

Key points

Training tool-use agents to improve from their own experience has long been a challenge in AI. Supervised fine-tuning relies on fixed teacher-distilled trajectories, while reinforcement learning with sparse rewards provides weak supervision for long-horizon interactions. A new paper from Hugging Face introduces DeepSearch-Evolve, a self-distillation framework that addresses this gap by leveraging a deterministic and verifiable environment called DeepSearch-World.

DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks. The environment supports reproducible search and page-reading tools, enabling key agentic cognitive behaviors such as progress verification, grounded reflection, and failure recovery. These features are essential for self-evolving agents.

The DeepSearch-Evolve framework iteratively performs trajectory generation, filtering, data mixing, and fine-tuning. Without distillation from more capable models, the resulting DeepSearch-World-9B model achieves competitive performance: 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA. These results demonstrate that verifiable environments enable scalable self-evolution for long-horizon web agents.

The authors plan to release the environment, the 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.

BenchmarkDeepSearch-World-9B
BrowseComp31.2%
GAIA61.5%
HotpotQA93.4%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1