AutoTool uses reinforcement learning with dual-mode rewards to train multimodal LLMs to adaptively choose between tool-assisted and text-centric reasoning, yielding accuracy and efficiency gains on V* and POPE benchmarks.
Meta AI Blog
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
Social identity markers in medical questions degrade LLM accuracy and uncertainty calibration, producing a calibration crisis that is non-additive for intersectional cases.
citing papers explorer
-
Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
AutoTool uses reinforcement learning with dual-mode rewards to train multimodal LLMs to adaptively choose between tool-assisted and text-centric reasoning, yielding accuracy and efficiency gains on V* and POPE benchmarks.
-
Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
Social identity markers in medical questions degrade LLM accuracy and uncertainty calibration, producing a calibration crisis that is non-additive for intersectional cases.