🛰️ Daily AI Frontier
‹ back to 2026-09-23

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents

Research LLM Agents

Ranking

Overall 85
Content 100
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Merged summary

TL;DR - CliffCompaction is an autocompaction method for long-horizon coding agents that cuts rollout costs by up to 50% while preserving or improving benchmark performance. It avoids cumulative context drift by retaining only selected original content rather than rewriting summaries.

  • Each compaction pass operates on the original context, discarding prior compacted output and only truncating or dropping information.
  • More efficient test-time scaling improved Terminal-Bench performance by over 10 percentage points for less than two full-context runs.
  • Parallel scaling enabled Kimi K2.6 to match Opus 4.7 and outperform Opus 4.6 and GPT-5.3 Codex at lower cost.
  • On KernelBench, million-token sessions produced CUDA speedups of 2.23Ă— after 200 steps and 3.58Ă— after 400 steps.

Sources (1)

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents

arXiv cs.AI Trang Nguyen, Eulrang Cho, Bingqing Chen, Tim Dettmers 2026-09-22 arXiv:2609.26779
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:14:33.862790 UTC

TL;DR - CliffCompaction is an autocompaction method for long-horizon coding agents that cuts rollout costs by up to 50% while preserving or improving benchmark performance. It avoids cumulative context drift by retaining only selected original content rather than rewriting summaries.

  • Each compaction pass operates on the original context, discarding prior compacted output and only truncating or dropping information.
  • More efficient test-time scaling improved Terminal-Bench performance by over 10 percentage points for less than two full-context runs.
  • Parallel scaling enabled Kimi K2.6 to match Opus 4.7 and outperform Opus 4.6 and GPT-5.3 Codex at lower cost.
  • On KernelBench, million-token sessions produced CUDA speedups of 2.23Ă— after 200 steps and 3.58Ă— after 400 steps.
item →