The results show that intervention-based diagnostics help identify stable-but-wrong and prior-tracking predictions that repeated agreement alone may miss, and a post-hoc, model-agnostic framework for accepting or rejecting individual VLM predictions is proposed, called Answer-Level Trust Selection (ATS).
This work proposes SAVLA, an end-to-end symmetry-aware VLA model for robust and data-efficient policy learning, which keeps the pretrained vision-language backbone entirely frozen while combining it with an equivariant flow-matching action head and a learned canonicalizer.
It is argued that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning, and the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart whose responses maximise utility in the steepest direction is formalised.
Comprehensive empirical evaluations demonstrate PEAR significantly improves average accuracy over the strongest debate baselines, and theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization.
Yang Feng, Ziwei Xu, Xia Hu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
