Avinatan Hassidim
Research Areas
Authored Publications
Sort By
Towards expert-level medical AI for real-time video consultations
Mahvish Nagda
Jihyeon Lee
Matthew Thompson
CJ Park
Tim Strother
Roma Ruparel
Teya Bergamaschi
Suhana Bedi
Meet Shah
Pavel Dubov
Toshiyuki Fukuzawa
Sam Schmidgall
Craig Schiff
Joseph Xu
Aliya Rysbek
Yana Lunts
Jan Freyberg
Rebecca Hemenway
David Racz
Carey Radebaugh
Joelle Barral
Kavi Goel
Kat Chou
James Manyika
Gregory Wayne
Yun Liu
Ethan Goh
Christina Chen
Ryutaro Tanno
arXiv (2026)
Preview abstract
Audio-visual interaction is the standard for patient-physician consultations, enabling natural communication and effective assessment of illness through non-verbal cues. While text-based AI has shown promise, it discards essential perceptual dimensions and limits patients who cannot articulate symptoms in writing. Early efforts to extend medical AI to audio-visual interaction have demonstrated feasibility, but not reached clinician-level performance. Here, we provide the first demonstration of expert-level AI in real-time clinical video consultations using AMIE (Articulate Medical Intelligence Explorer) in a video configuration. AMIE (Video) is a Gemini-based multi-agent system integrating low-latency dialogue, clinical reasoning, and real-time audio-visual perception. To guide development, we established a taxonomy and automated evaluations for clinical audio-visual cues in telehealth settings. In a randomized Objective Structured Clinical Examination (OSCE) study with 30 primary care physicians (PCPs), 15 patient actors and 100 clinical scenarios, we compared AMIE (Video), its text-only counterpart AMIE (Text), and PCPs consulting via video. Clinical evaluators rated AMIE (Video) on par or better than PCPs in history-taking, diagnosis, management, and physical observation and examination. Patient actors preferred AMIE's approach to assessing and explaining conditions, while PCPs were preferred for rapport and partnership building. In modality ablation, patient actors preferred AMIE (Video)'s interface over text chat for communicative effectiveness, convenience, and feeling understood. Limitations remain in fine anatomical precision, subtle affective nuances, and high-frequency movements. While further research is needed before real-world translation, these results mark an important milestone toward AI systems capable of augmenting care across the sensory complexity of clinical practice.
View details
Towards conversational artificial intelligence for disease management
Khaled Saab
David Stutz
Yong Cheng
Kavita Kulkarni
Sara Mahdavi
Joelle Barral
James Manyika
Ryutaro Tanno
Adam Rodman
Nature (2026)
Preview abstract
Although large language models have shown promise in diagnostic dialogue, their capabilities for effective management reasoning, including disease progression, therapeutic response and safe medication prescription, have remained underexplored. We have advanced the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) using a new large-language-model-based agentic system optimized for multivisit clinical management and dialogue. To ground the reasoning of AMIE in authoritative clinical knowledge, we leveraged the long-context capabilities of Gemini, combining in-context retrieval with structured reasoning to align its output with up-to-date clinical practice guidelines and drug formularies. In a randomized, blinded virtual Objective Structured Clinical Examination study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multivisit case scenarios designed to reflect the guidance of the UK National Institute for Health and Care Excellence and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning, as assessed by specialists, and scored better both with respect to preciseness of treatment and investigation, and in terms of its alignment with and grounding in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark that was derived from two national drug formularies (from the USA and UK) and validated by board-certified pharmacists. Although AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher-difficulty questions. Although further research will be needed before real-world translation of AMIE, its strong performance across evaluations marks a significant step towards use of conversational artificial intelligence as a tool in disease management.
View details
Conversational diagnostic artificial intelligence in ambulatory primary care: a prospective feasibility study
Peter Brodeur
Jacob M. Koshy
Khaled Saab
Ava Homiar
Roma Ruparel
Charles Wu
Ryutaro Tanno
Joseph Xu
Amy Wang
David Stutz
Hannah M. Ferrera
David Barrett
Lindsey Crowley
Jihyeon Lee
Spencer E. Rittner
Selena K. Zhang
Elahe Vedadi
Christine G. Kohn
Kavita Kulkarni
Vinay Kadiyala
Sara Mahdavi
Wendy Du
David Feinbloom
Renee Wong
Petar Sirkovic
Alessio Orlandi
Juro Gottweis
Joelle Barral
Kat Chou
James Manyika
Rob Fields
Jonathan X. Li
Marc L. Cohen
Adam Rodman
The Lancet (2026)
Preview abstract
Background: Artificial intelligence (AI)-based systems show promise for assisting primary care providers (PCPs) with patient care. We aimed to evaluate the safety and quality of clinical conversations of a patient-facing conversational AI system, which engaged in real-world urgent primary care appointments.
Methods: In this prospective, single-centre, single-arm feasibility study, English-speaking patients aged at least 18 years interacted with the Articulate Medical Intelligence Explorer (AMIE) up to 5 days before a single-complaint urgent primary care appointment. Physician safety supervisors monitored all interactions and were trained to intervene on the basis of predefined safety criteria. AMIE transcripts and summaries were shared with PCPs before the visit. Primary outcomes were the number of supervised conversation safety stops, AMIE’s conversation quality assessed by clinical evaluators, and patient and PCP experiences per surveys. This study is registered with ClinicalTrials.gov (NCT06911398).
Findings: From April to November, 2025, 114 patients were enrolled with 98 completing both the AMIE interaction and the PCP appointment. Zero conversation safety stops were required on the basis of prespecified criteria. Safety supervisors noted one hallucination and added clinical information in five interactions. AMIE’s conversations were rated favourably in 87–100% of cases (17 criteria) by clinical evaluators, and 48–96% (16 criteria) by patients. Patient attitudes towards AI improved after interacting with AMIE and remained elevated after the patient’s visit with their physician. PCPs completed post-surveys in 60 of 98 cases, including 44 cases in which they reviewed the AMIE transcript before the visit. PCPs found AMIE helpful for visit preparation in 33 of 44 cases and reported that it might have changed their behaviour in 25 of 44 cases.
Interpretation: Although further research is needed, this study shows the initial feasibility of conversational AI in a real-world setting—assessed via conversation safety and quality, as well as user acceptance—and represents a crucial step towards clinical translation.
Funding: Alphabet.
View details
Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs
Guy Mor-Lan
Omer Goldman
Matan Eyal
Adi Mayrav Gilady
Sivan Eiger
Reut Tsarfaty
ACL (2026) (to appear)
Preview abstract
Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work, we aim to quantify models' inter- and intra-lingual biases, via their ability to answer locale-ambiguous questions. To this end, we present LocQA, a test set containing 2,156 questions in 12 languages, referring to various locale-dependent facts such as laws, dates, and measurements. The questions do not contain indications of the locales they relate to, other than the querying language itself. LLMs' responses to LocQA locale-ambiguous questions thus reveal models' implicit priors. We used LocQA to evaluate 32 models, and detected two types of structural biases. Inter-lingually, we show a global bias towards answers relevant to the US-locale, even when models are asked in languages other than English. Moreover, we discovered that this global bias is exacerbated in models that underwent instruction tuning, compared to their base counterparts. Intra-lingually, we show that when multiple locales are relevant for the same language, models act as demographic probability engines, prioritizing locales with larger populations. Taken together, insights from LocQA may help in shaping LLMs' desired local behavior, and in quantifying the impact of various training phases on different kinds of biases.
View details
WAXAL: A large-scale multilingual African language speech corpus
Abdoulaye Diack
Perry Nelson
MohamedElfatih MohamedKhair
Emmanuel Asiedu Brempong
Tavonga Siyavora
Bob MacDonald
Uche Okonkwo
Sandy Ritchie
Mandy Jordan
Abhishek Bapna
Vusumuzi Dube
Jason Hickey
Ronit Levavi Morad
Jeff Dean
Aisha Walcott-Bryant
2026
Preview abstract
Recent advances in speech technology predominantly favor high-resource languages, leaving speakers of Sub-Saharan African languages underserved. To bridge this divide, we introduce WAXAL, an open, large-scale speech dataset spanning 24 African languages representing over 100 million speakers. WAXAL comprises over 14,100 hours of speech collected in partnership with African academic and community organizations to build local research capacity: an Automatic Speech Recognition (ASR) corpus with 2,340 hours of transcribed, image-prompted natural speech across 19 languages (plus ~11,760 untranscribed hours) and a studio-quality Text-to-Speech (TTS) corpus exceeding 235 hours. We empirically benchmark three architecturally distinct ASR models---Gemma 3n 2B, Whisper-Large-v3, and MMS-1B-all---across the 19 ASR languages on strictly speaker-disjoint splits. Fine-tuning on WAXAL yields substantial gains, reducing macro-average WER by up to 58% for Whisper-Large-v3, 56% for Gemma 3n 2B, and 17% for MMS-1B-all (and Character Error Rate by up to 70%). WAXAL-fine-tuned models generalize zero-shot to three out-of-distribution benchmarks---FLEURS, Mozilla Common Voice, and Sunbird SALT---and outperform FLEURS-trained baselines in bidirectional cross-dataset transfer. Finally, an LLM-as-judge semantic evaluation confirms that fine-tuning preserves speaker intent beyond surface-level transcription metrics. WAXAL is publicly released under a CC-BY-4.0 license at https://huggingface.co/datasets/google/WaxalNLP
View details
Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation
Aliza Hoffman
Gal Moshitch
Aaron Bell
Roy Lee
William Cai
Adam Boulanger
Mark Young
Utkarsh Patel
Ruth Alcantara
Zachary Luna
Sydney Lin
Ollie Guinan
Christopher Haire
Lily Mihalkova
Luke Barrington
Tim Thelin
Gil Fidel
Ronald Ho
Samapriya Roy
Shravya Shetty
Mandar Sharma
Tyler McHenry
Joydeep Paul
Aviv Slobodkin
Jamie McPike
Noam Slonim
Per Bjornsson
Reuven Sayag
Allison Berman
Niv Efron
Gia Jung
arXiv (2026)
Preview abstract
Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA), a Gemini-powered research system that combines geospatial data sources, foundation models, and tools to answer questions about our planet. GRA organizes these into modular domain skills and pairs them with upfront geospatial planning to decompose complex queries into multi-stage workflows. Evaluating such systems is hard: real-world problems admit multiple valid workflows, require data discovery across large catalogs, and rely on evolving ground truth. We introduce two benchmarks and release their development splits. GeoExpertQueries poses complex analytical problems grounded in practitioner use cases and refined by geospatial experts; each is paired with a consensus golden workflow from three independent experts and scored by a human-validated, tool-agnostic autorater. GeoKTools consists of templated queries with deterministic reference solvers that systematically vary the number of required tool types. We also use two external benchmarks, CBGB and UnivEARTH; the latter we find to be saturated. To isolate the contribution of GRA's tools and its agentic orchestration, we compare four configurations, each with Gemini 3.1 Pro and 3.8 Flash: a standalone LLM, the LLM with basic tools, the LLM with GRA's skills and tools but without its upfront planning and execution guidance, and GRA itself. With at most basic tools, an advanced model recovers much of the answer on templated queries but satisfies only a small fraction of the expert workflows on open-ended problems; GRA performs well on both. The largest step comes from GRA's skills and tools; on open-ended problems, its planning and execution guidance add a further gain with Gemini 3.8 Flash, letting Flash match or exceed Pro at lower cost.
View details
Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery
Zach Cutts
John Coller
Rachel Chen
Hua Tang
Ryder Easterlin
Dina Zverinski
Petar Sirkovic
arXiv preprint arXiv:2610.24806 (2026)
Preview abstract
Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than iterative improvement. Whether large language model (LLM)-based reasoning agents can accelerate de novo discovery by iterating with lab data remains unproven.
Here we use protein-binding aptamer design as a sandbox (1-2 week cycles, $1-$3 per candidate) to demonstrate a wet lab in a closed loop with AI systems. We tasked agentic pipelines with developing aptamer binders against α-thrombin and myoglobin across three design-test-improve cycles (∼1,000 candidates per round; ∼4,400 constructs). Statistically significant, bead-corrected on-target hit rates among new candidates rose across rounds from 0.0% in Round 1 to 26.0% in Round 2 and 42.1% in Round 3 on α-thrombin (37.1% excluding literature motif descendants), and from 10.2% in Round 1 to 3.7% in Round 2 and 33.5% in Round 3 on myoglobin. Single-clone bead-binding titrations of eight full-length α-thrombin candidates confirmed concordance with pooled sequencing enrichment (Pearson r=0.90). In these assays, literature-derived motifs engineered by the agents to reduce off-target reactivity in the pooled screen reached apparent affinities of KD=24.6--133 nM, whereas de novo scaffolds showed low-micromolar binding (KD>1 μM).
We also report how our pipelines used myoglobin binding data to exploit the G-quadruplex binder space, diagnose cross-reactivity as on-target specificity dropped from 75.0% to 19.1%, and recover by developing strategies that restored specificity to 72.4%. We demonstrate that empirical lab data is more valuable than existing computational proxies, showing how iterative experimental feedback enables AI agents to diagnose assay artifacts and refine molecular designs across rounds.
View details
Prospective evidence for conversational medical AI is hard, but non-negotiable
Adam Rodman
Ami Parekh
Ethan Goh
Christina Chen
Joelle Barral
Nature Medicine (2026)
Preview abstract
Trust in clinical artificial intelligence (AI) cannot be benchmarked into existence. It must be earned through rigorous prospective studies in real-world clinical settings, where the hardest lessons often concern the humans and systems around the AI, not the technology itself.
View details
Fine-grained Measurement of Vehicle Delay Fairness
Eliav Buchnik
Tom Kalvari
Jack Haddad
Dan Karliner
Danny Veikherman
Ron Tsibulsky
Shai Ferster
Ori Rottenstreich
2025
Preview abstract
Optimizing signal timing in traffic lights helps to improve traffic flow and reduce emissions through reducing delays. At intersections, vehicles from different movements observe different delays impacted by the traffic light plan. This paper analyzes delay fairness among various vehicles at intersections. We refer to three cities: Rio de Janeiro, Hamburg and Seattle with a total number of over 5100 intersections. We present an intuitive methodology to compute delay fairness based on Gini index, a common fairness measure in economics. We evaluate the fairness based on real traffic data and provide insights on the relationship of fairness with day hours and traffic demand. We also examine real changes in traffic light plans that occurred in practice to check whether improving delay is often aligned with increasing fairness.
View details
Generative AI for medical education: Insights from a case study with medical students and an AI tutor for clinical reasoning
Amy Wang
Roma Ruparel
Paul Jhun
Julie Anne Seguin
Patricia Strachan
Renee Wong
CHI (2025) (to appear)
Preview abstract
Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), have demonstrated significant potential in clinical reasoning skills such as history-taking and differential diagnosis generation—critical aspects of medical education. This work explores how LLMs can augment medical curricula through interactive learning. We conducted a participatory design process with medical students, residents and medical education experts to co-create an AI-powered tutor prototype for clinical reasoning. As part of the co-design process, we conducted a qualitative user study, investigating learning needs and practices via interviews, and conducting concept evaluations through interactions with the prototype. Findings highlight the challenges learners face in transitioning from theoretical knowledge to practical application, and how an AI tutor can provide personalized practice and feedback. We conclude with design considerations, emphasizing the importance of context-specific knowledge and emulating positive preceptor traits, to guide the development of AI tools for medical education.
View details
