Machine Heart
Nov 12, 2026 · Artificial Intelligence
CoACT: 33% Token Reduction for Coding Agents via Action-Preserving Compression
Tsinghua researchers propose CoACT, an observation compression method for coding agents that preserves the agent's next action, cutting token consumption by 33% on SWE-bench Verified while maintaining pass rates, using a two-stage training approach and a Next-Action Preservation criterion.
AI for Software EngineeringCoding AgentsICSE 2027
0 likes · 11 min read