When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical reasoning can change future actions and the resulting interaction trajec...
Ming-Xuan Wang, Fei Luo, Bo Wang et al.
· 0 citations