We have 8 of 36 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Methods for assessing language-model agents include rule checkers over logs, analyses of skill coverage and composition, support checkers, prefix monitors, execution gates, and rare-event estimators. Each observes a different part of a run and makes a claim of a different strength, and no common account says how these...
This work introduces PrefixGuard, a neuro-symbolic method that uses learned events to connect online failure warning with finite-state execution diagnosis with finite-state execution diagnosis in large language model (LLM) agents.
It is found that a simple random-without-replacement routing policy, which lets each agent debate with two distinct and newly sampled peers at every round, provides a surprisingly strong baseline and consistently improves the accuracy-cost trade-off of sparse MAD.
Cross-modal evidence noncommutativity is revealed: the same evidence can lead to different judgments when its order changes, and placing perceptual evidence later can increase the model's reliance on its content.
This paper introduces SCOPE (Sequential Conformal OOD Probing and Evaluation), a framework that selects a readable hidden layer, constructs a conformal gate with IND calibration, and uses a supermartingale e-process to certify persistent service-boundary evidence.
FragileFlow is introduced, a plug-in regularizer that uses a calibrated margin buffer to identify correct-but-fragile predictions and organize their off-class probability mass into a class-wise vulnerable-risk matrix and provides the first PAC-Bayes upper bound for this margin-aware error-flow object.
The Reasoning Backroom is established as a general AI provenance problem whose audit requires intervention because of a pervasive provenance failure in multi-agent systems.
This work proposes Logical Graph Uncertainty (LGU), a framework that explicitly models implication and incompatibility among answers, and ranks first on average among existing uncertainty measures.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
