ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay 事件

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay arXiv:2605.28069v1 Announce Type: new Abstract: Adaptive context compression is vital for scaling Large Language Models (LLMs) to complex, multi-turn agent tasks. However, rule-based compression methods may discard task-critical nuances, while Reinforcement Learning (RL) approaches usually struggle to balance information retention and token efficiency under the sparse rewards inherent to long-horizon workflows. To bri