LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
task-X" /> This clears the current owner and resets the task to pending. Then reassign it with <assign_task id=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.