Preprint
Aug 2026
MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
This work proposes MESA (a Multi-structure Evidence Selection framework for long-horizon Agent), which builds five complementary structure views of each trajectory and learns from end-to-end answer-level feedback to select and fuse a query-specific subset for a frozen answer model.
Beidi Zhao, Yaoqi Chen, Yuru Feng et al.
· 0 citations