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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
VRRL trains LVLMs for visually grounded self-reflection via prefix masking and buffered roll-ins, yielding higher out-of-distribution accuracy on grounding and navigation tasks than standard RL baselines.
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.
-
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning
VRRL trains LVLMs for visually grounded self-reflection via prefix masking and buffered roll-ins, yielding higher out-of-distribution accuracy on grounding and navigation tasks than standard RL baselines.