No AI summary available for this article.
Why It Matters
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50% under a bounded context while maintaining or improving performance on Terminal-Bench and achieving new levels of efficiency for test-time scaling and state-of-the-art results on KernelBench. The per-rollout savings of CliffCompaction make the performance--cost trade-off of test-time scaling more efficient, adding over 10 percentage points on Terminal-...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.26779v1 · Indexed about 2 hours ago