3 papers
cs.AI2026
StateComp: Learning When to Compress History in Long Horizon Agents
Mingxuan Wang, Hongyue Chen, Yinglong Guo +6
Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing context…
cs.AI2026
Memory Control Signals Emerge Before Action in Long Horizon Agents
Mingxuan Wang, Guorun Yao, Fei Luo +6
Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existi…
cs.AI2026
DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents
Mingxuan Wang, Bo Wang, Fei Luo +6
Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Existing compression strategies…