CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding 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
Public signals
N/A
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.