Researchers propose MARS, a Monte Carlo Tree Search-based framework for automatically repairing multi-agent systems, and introduce StateMAS, a benchmark with 1,310 replayable failure trajectories. On …
Researchers Henry Gao and Jinho D. Choi have developed a task-oriented dialogue system that uses large language models with in-context prompting and unstructured conversational logs, eliminating the n…
Researchers introduced MARS, a training-free method that enhances safety in multimodal large language models by leveraging textual refusal directions to steer model outputs away from unsafe content. T…
Researchers introduced Modality-Agnostic Refusal Steering (MARS), a method that uses text-based refusal strategies to enhance safety in multimodal language models without requiring unsafe multimodal d…