FS-Researcher achieves state-of-the-art report quality on deep research benchmarks by using a file-system-based dual-agent framework that scales test-time compute beyond context limits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
FS-Researcher achieves state-of-the-art report quality on deep research benchmarks by using a file-system-based dual-agent framework that scales test-time compute beyond context limits.