A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification of medical abstracts. The work addresses the disagreement problem in Explainable Artificial Intelligence, where different attribution methods produce divergent explanations for the same input and prediction. A natural...
Javier Diaz Esteban-Herreros, David Mu\~noz-Valero, Raquel Mart\'inez-Espa\~na et al.· 0 citations
Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows the context, self-correction diverges, tool demonstrations loop, and tasks are silently abandoned. We present evidence, from a controlled single-machine comparison and o...
Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly influence acuity assignment. Although open-source large language models (LLMs) are increasingly considered for local and privacy-preserving clinical decision support,...
Manar Aljohani, Brandon Ho, Kenneth W. McKinley et al.· 0 citations
The results highlight that instruction following, rather than token entropy alone, can drive generation diversity, and enable Gacha to invert the long-observed tension between diversity and model capability.
Scott Geng, Yu-Fei Zhang, J. Lee et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A waveform-label pair does not preserve this knowledge. We propose a generation-provenance substrate in which a synthetic research object binds source specification, generated...
Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds. We introduce DAYJOB, a benchmark of 130 tasks built by professionals in healthcare (50) and finance (80). The tasks are estimated to take a profes...
Stephanie Finley, Liudas Panavas, T. Mikkelson et al.· 0 citations
Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors do not jointly decide which test to acquire or when the available evidence is sufficient for diagnosis. We propose SCOPE-AD (Sequential Cost-Aware Ordinal-Belief Plann...
Ziwen Yu, Ivan Koychev, Elizabeth Coulthard et al.· 0 citations
Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task binding. We therefore study \emph{dynamic task routing}, in which an event stream revises task bindings and a system must sel...
Yang-Hao Luo, Selim-Antoine Lali, Jeremy Moebel et al.· 0 citations
A chatbot that says"I will remind you tomorrow"will not run again until the user writes. We call such a promise an empty commitment: a promise of action after the current turn that nothing in the agent's tools or runtime can carry out. Unlike a broken promise, its emptiness is decided by the agent's configuration at th...
Jia-Qi Tang, Bingyu Shen, Lan Wei et al.· 1 citation
Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effective communication, a favorable agent architecture, or simply additional reasoning? Because communication methods are commonly evaluated within...
Shi-Xuan Li, Wei Yang, Pei-Yu Zhang et al.· 0 citations
Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the task, which agent to trust with each subtask, and when to create a new specialist are all...
Xue-Hang Guo, Hao-Yu Wang, Sheng-Yu Chen et al.· 0 citations
This work forms this missing dimension of harness optimization as an automated curriculum learning problem and introduces ActiveSaddler, which establishes automated curriculum learning as a new crucial optimization dimension for harness optimization.
Sungho Park, Wonjoong Kim, Jue Zhang et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
