Data Party THU
Nov 17, 2026 · Artificial Intelligence
CoACT: How Tsinghua Cut Coding Agent Token Costs by 33% Without Losing Performance
Tsinghua researchers propose CoACT, an observation compression method for coding agents that preserves the agent's next action, reducing token consumption by 33% on SWE-bench Verified while maintaining task success rates across three LLM models.
CoACTCoding AgentICSE 2027
0 likes · 10 min read
