arXiv subjects

Deepak Bansal

Publications and source records attributed to Deepak Bansal.

4 recordsLinked to original sources

arXiv2026

PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents

Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Primary care guards against diagnostic errors and unsafe care; agents assisting in this domain warrant evaluation against the same risks. Current benchmarks focus on medical knowledge, assessed through isolated question-answering or clinician-facing tasks. PatientAgentBench benchmarks patient-facing agentic healthcare; it evaluates a foundation model, wrapped in an agent with a sandbox of healthcare tools, conversing with a simulated patient. Each conversation is scored by an LLM-as-a-Jury across six dimensions via over a hundred conversation-agnostic, clinician-grounded criteria. To validate alignment, licensed clinicians annotated shared conversations, yielding 79-93% adjacent agreement between jury and expert raters, on par with or exceeding clinician inter-rater agreement. We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps. Triage quality is the most discriminating dimension: pass rates rise from 32% for the weakest models to 88% for the strongest, with agents often acting on administrative requests without clinical screening. Clinical safety and workflow accuracy follow the same pattern: the weakest models fail often, fabricating unexecuted actions, while frontier models fail on only 1-3% of cases, from unverified tool outputs and omitted crisis resources in an emergency. More capable models narrow these gaps but do not close them; the strongest scores only 4.25 of 5 overall. These failures surface only in sustained, tool-using conversations against realistic patient records, confirming that static benchmarks are insufficient as healthcare agentic systems gain autonomy. We release the framework as a reproducible, clinician-validated evaluation standard to help the field close this gap.

cs.AI↗

arXiv2026

IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations

Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging. However, existing medical AI benchmarks are fragmented: some support multi-turn dialogues but lack images, while others provide multimodal inputs but focus on single-turn QA tasks. To address this gap, we introduce IMCBench, an image-grounded, multi-turn medical conversation benchmark that pairs real, publicly available clinical images with synthetic patient profiles to simulate realistic patient-clinician interactions. Each conversation is evaluated across three clinical dimensions: safety, accuracy, and appropriate use of uncertainty in diagnosis. We benchmark eight multimodal frontier models across four model families (Claude, GPT, Nova, and Llama), scoring each on a 1-5 scale using LLM-as-Jury scoring calibrated against expert clinician annotations. Our results show that Claude Opus 4.6 achieves the highest overall score (3.61), followed by Claude Sonnet 4.6 (3.30) and GPT-5.2 (3.29), though no model dominates all dimensions and safety degrades for both malignant and rare conditions ($\Delta$ = -0.27 each). Ablation studies further reveal that both visual input and EHR context contribute to safe guidance (safety drops of 0.18 and 0.23 on average when each is removed), with stronger models leveraging visual features more effectively. Together, these findings demonstrate that accurate clinical description does not guarantee safe patient guidance, motivating the need for multi-dimensional evaluation frameworks in medical AI.

cs.AI↗

arXiv2021

Geometric properties of some generalized Mathieu power series inside the unit disk

We consider two parametric families of special functions: One is defined by a power series generalizing the classical Mathieu series, and the other one is a generalized Mathieu type power series involving factorials in its coefficients. Using criteria due to Fejer and Ozaki, we provide sufficient conditions for these functions to be close-to-convex or starlike inside the unit disk, and thus univalent.

math.CV↗

arXiv2001

System Support for Bandwidth Management and Content Adaptation in Internet Applications

This paper describes the implementation and evaluation of an operating system module, the Congestion Manager (CM), which provides integrated network flow management and exports a convenient programming interface that allows applications to be notified of, and adapt to, changing network conditions. We describe the API by which applications interface with the CM, and the architectural considerations that factored into the design. To evaluate the architecture and API, we describe our implementations of TCP; a streaming layered audio/video application; and an interactive audio application using the CM, and show that they achieve adaptive behavior without incurring much end-system overhead. All flows including TCP benefit from the sharing of congestion information, and applications are able to incorporate new functionality such as congestion control and adaptive behavior.

cs.NI↗