DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks
Record details
Published: 7 July 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 22 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Reliable and Developer-Aligned Evaluation of Agents for Software Engineering
arXiv · 7 July 2026
From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations
arXiv · 7 July 2026
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
arXiv · 7 July 2026
Social cognitive architecture for NPC groups: integration of transformer theory of mind and hierarchical reinforcement learning
Artificial Intelligence Review · 7 July 2026
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
HuggingFace Daily Papers · 8 July 2026
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
HuggingFace Daily Papers · 8 July 2026
How to cite this record
ethics.ai (7 July 2026), “DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment,” evidence record 12312, https://ethics.ai/record/12312 (originally published by HuggingFace Daily Papers).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.