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.
MapReduce: Simplified data processing on large clusters
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
An MTJ-based logic-in-memory design performs fully parallel stochastic bit-stream generation and arithmetic without external random number generators by exploiting device stochasticity.
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.
-
Maximizing Memory-Level Parallelism via Integrated Stochastic Logic-in-Memory Architectures
An MTJ-based logic-in-memory design performs fully parallel stochastic bit-stream generation and arithmetic without external random number generators by exploiting device stochasticity.