1
ACON: Optimizing Context Compression for Long-horizon LLM Agents
最新论文提出ACON方法，优化长时域LLM代理的上下文压缩，显著提升推理效率与准确性。
arXiv:2510.00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environment…