Tag
Microsoft has removed its FastContext model from Hugging Face and GitHub, with no official explanation yet.
Notes on Microsoft's FastContext technique and a small experiment on software engineering QA with retrieval hints.
A Microsoft and SJTU research paper introduces FastContext, a dedicated exploration subagent for coding agents that separates repository navigation from task solving, reducing orchestrator token usage by up to 60% and improving resolution rates by 5.5% on SWE-bench benchmarks.
Microsoft's FastContext is a trending paper introducing a small 4B model for efficient code retrieval paired with coding agents, rivaling closed-source systems on SWE-Bench Multilingual.
Microsoft released FastContext-1.0, a lightweight repository-exploration subagent for LLM coding agents that reduces main-agent token consumption by up to 60% while improving resolution rates by up to 5.5%.