R esear S tudio: A Human-intervenable Framework for Building Controllable Deep Research Agents

Yang, Linyi, Weng, Yixuan · 2025 · DOI 10.18653/v1/2025.emnlp-demos.69

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

open at publisher browse 1 citing papers

representative citing papers

cs.CL · 2026-07-13 · conditional · novelty 5.5

ToFu beats Claude Code and OpenCode on SWE-bench Verified Pass@1 across three LLMs while using about 28% fewer tokens than Claude Code on average.

Showing 1 of 1 citing paper.

ToFu: A White-Box, Token-Efficient Agent Harness for Researchers cs.CL · 2026-07-13 · conditional · none · ref 38
ToFu beats Claude Code and OpenCode on SWE-bench Verified Pass@1 across three LLMs while using about 28% fewer tokens than Claude Code on average.