FastContext: Specialized Exploration Subagent Cuts Coding Agent Token Usage by 60%
Microsoft / Shanghai Jiao Tong University
FastContext decouples repository exploration from task-solving in LLM-based coding agents by introducing a dedicated exploration subagent (4B–30B parameters) that issues parallel read/glob/grep tool calls and returns compact file-path and line-range citations to the main solver. Training uses supervised fine-tuning followed by task-grounded reinforcement learning. Integrated into Mini-SWE-Agent, FastContext improves resolution rates by up to 5.5 percentage points on SWE-bench Multilingual, SWE-bench Pro, and SWE-QA, while cutting main-agent token usage by up to 60%.
Why it matters
Repository navigation is a major hidden cost in frontier coding agents — models burn large portions of their context window just locating relevant files. FastContext's separation-of-concerns approach shows that a specialized small model can handle exploration far more efficiently than a monolithic solver. 152 upvotes on HuggingFace Daily Papers.
Importance: 3/5
Practical 60% token reduction for coding agents with improved SWE-bench results; 152 HF Daily upvotes (+1 bump); from Microsoft Research with immediate relevance for agent pipeline designers.