CMU & Meta Open-Source ACM: Agents Learn to Compress Context Autonomously, Cutting Peak Tokens 20%

aigclink · x · 2026-08-06

CMU and Meta open-sourced the Agentic Context Management (ACM) framework, addressing the context bottleneck in long-horizon agentic tasks.

Unlike traditional heuristic-based truncation or summarization, ACM equips models with two core tools:

Researchers noted that frontier models like GPT-5.5 rarely use these tools natively. To solve this, they designed a bidirectional teacher-student distillation pipeline where a 397B model teaches a 9B model when to compress versus when to keep searching. The trained Qwen3.5-9B achieved a 27% relative improvement on BrowseComp-Plus—rivaling open-source models 40x its size—while reducing peak token usage by 20%.

Original post →

More from coding & agent

coding & agent channel →