FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
Quick summary
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilution. Existing context-compression methods learn what to discard offline: by contrastively optimizing guidelines, distilling compressors, or training compression policies. This incurs a substantial cost. Further, the compression policy is learned a priori and is not dynamically conditioned on the evolving test-time trajectories. In this paper we ask a complementary question: Which
Key takeaways
- arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilution.
- Existing context-compression methods learn what to discard offline: by contrastively optimizing guidelines, distilling compressors, or training compression policies.
- Further, the compression policy is learned a priori and is not dynamically conditioned on the evolving test-time trajectories.
Why it matters
The significance is not only the legal text but how it changes product design. Decisions around “FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents” may reshape data collection, model training, output accountability and market access.
Member comments