ACGM learns task-adaptive sparse graphs over multi-modal agent histories via policy-gradient optimization, reaching 82.7 nDCG@10 and 89.2% Precision@10 on WebShop, VisualWebArena, and Mind2Web while outperforming 19 baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
ACGM learns task-adaptive sparse graphs over multi-modal agent histories via policy-gradient optimization, reaching 82.7 nDCG@10 and 89.2% Precision@10 on WebShop, VisualWebArena, and Mind2Web while outperforming 19 baselines.