ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Paper • 2606.07591 • Published • 102
09. Investigación
-
-
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 55 -
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Paper • 2606.10728 • Published • 36 -
Towards Diverse Scientific Hypothesis Search with Large Language Models
Paper • 2606.10587 • Published • 2 -
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Paper • 2606.11662 • Published • 10 -
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 31 -
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Paper • 2606.16905 • Published • 7 -
Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
Paper • 2606.18648 • Published • 15 -
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Paper • 2606.24530 • Published • 66 -
Towards Automating Scientific Review with Google's Paper Assistant Tool
Paper • 2606.28277 • Published • 11 -
AI translation of literary texts is "fine", but readers still prefer human translations
Paper • 2606.26040 • Published • 9