Self-Compacting Language Model Agents

Key points

Fixed token-threshold compression can trigger in the middle of reasoning or retrieval and accidentally delete verified facts.
The method combines a compression tool that the model can call directly with a lightweight rubric that says to compress when a subtask is solved and suppress compression during reasoning.
When the tool is provided without the rubric, usage varies widely across models and is often invoked at the wrong time, which shows that the rubric is essential.
On math benchmarks such as IMO-Answerbench and HMMT, it improves by up to 18.1 points over the no-compression baseline.
On agentic search tasks such as BrowseComp, it improves by 5 to 9 points while reducing token cost by 30 to 70 percent per question.
Adaptive compression is possible at inference time alone, without any fine-tuning or external supervision.

External research summaries. These are not HDATF publications or measured product results.