MPLMs let LLM threads pass messages to achieve asymptotically smaller context on Sudoku, early termination on 3-SAT, and competitive long-context QA results compared with CoT and fork-join baselines.
The First Workshop on System-2 Reasoning at Scale, NeurIPS'24 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Message Passing Enables Efficient Reasoning
MPLMs let LLM threads pass messages to achieve asymptotically smaller context on Sudoku, early termination on 3-SAT, and competitive long-context QA results compared with CoT and fork-join baselines.