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 Twelfth International Conference on Learning Representations , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
RADAR generates query-adaptive multi-agent communication structures via conditional discrete graph diffusion guided by effective graph size, outperforming baselines on accuracy and token consumption across six benchmarks.
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.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
RADAR generates query-adaptive multi-agent communication structures via conditional discrete graph diffusion guided by effective graph size, outperforming baselines on accuracy and token consumption across six benchmarks.