CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents· CliffCompaction: 长周期代码代理的高效压缩技术
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-Bench for less than the cost of two full-context runs. Under parallel test-time scaling, CliffCompaction lets Kimi K2.6 match Opus 4.7, and exceed Opus 4.6 and GPT-5.3 Codex at lower cost. The key to
为长周期代码代理开发高效压缩技术，显著降低成本。
- 核心方法
- 提出CliffCompaction自压缩技术，通过在限定上下文内减少Token数量来降低成本，同时保持或提升性能。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 长周期代码代理在处理复杂问题时需要大量上下文，导致成本高昂且受上下文窗口限制。
- 关键实验
- 实验表明CliffCompaction在Terminal-Bench上提高了10个百分点以上，且在平行测试时扩展下，Kimi K2.6以更低的成本匹配甚至超过Opus 4.7的性能。
- 主要贡献
- CliffCompaction在Terminal-Bench和KernelBench上取得显著效率和性能成果，降低了测试时扩展的成本。
- 意义与局限
- 该技术使得长周期代码代理的性能成本比更加优化，但可能需要进一步验证其在其他任务和环境下的通用性。