Searcharxiv⌕ Search

arXiv subjects

Benyou Wang

Publications and source records attributed to Benyou Wang.

At least 19 recordsLinked to original sources

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

cs.CV↗

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they track broader phone-use performance and increase when visual input is removed. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act. Code and public data: \url{https://github.com/tangzhy/PhoneSafety}.

cs.CL↗

MedSonor: Learning to Use Clinical Audio in Medical LLMs

Clinical audio conveys medical information that transcripts may not preserve, but using it in medical responses requires interpreting it alongside clinical requests and dialogue context. Existing medical audio supervision largely targets classification or recognition, while general audio-language models lack specialized medical knowledge and direct feedback for open-ended responses. We present MedSonor, a medical dialogue model integrating medical knowledge, spoken dialogue, and clinical audio understanding. We pair authentic medical audio with clinical requests and combine these audio-integrated dialogues with collected medical audio and synthesized spoken dialogues for supervised fine-tuning, followed by two stages of rubric-guided reinforcement learning. We introduce MedVoice-Dial and MedVoice?AID to evaluate responses within supplied multi-turn medical contexts and to requests involving clinical audio, respectively. Across seven medical benchmarks, MedSonor outperforms the evaluated general-purpose open-weight audio-language baselines and ranks highest in aggregate physician preference evaluation, while broadly retaining general speech capabilities.

cs.SD↗

Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning

Legal question answering requires answers that are not only plausible, but also grounded in legally valid and citable evidence. Standard retrieval-augmented generation often relies on one-shot semantic matching, which is insufficient when legal evidence must be selected according to authority, applicability, and diversity across heterogeneous sources. We introduce Legal-R1, an agentic retrieval framework for evidence-based legal reasoning. Legal-R1 decomposes legal reasoning into a multi-agent workflow, where a Lawyer agent learns when to retrieve, which legal source to query, what evidence to seek, and when the collected evidence is sufficient. A Legal Assistant agent retrieves from normative legal sources and precedent cases with authority-aware and diversity-aware selection, while a Judge agent generates the final answer from the complete evidence trajectory. We post-train only the Lawyer agent with masked supervised fine-tuning and trajectory-aware reinforcement learning. Experiments on multiple Chinese legal benchmarks show that Legal-R1 improves over general-purpose, legal-specific, and retrieval-augmented baselines.

cs.CL↗

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models

Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and introduces additional complexity through multi-stage optimization. These limitations motivate RL-only adaptation. However, pure on-policy RL suffers from a cold-start problem, while mixed-policy RL still falls short: informative tokens in teacher outputs are learned too slowly in early training, and stale teacher outputs can hinder later improvement. We identify these two failure modes as Gradient Starvation and Teacher-Distribution Anchoring. To address them, we propose One-stage Policy Optimization (OnePO), which treats teacher outputs as transient guidance for policy improvement. OnePO combines Adaptive Objective Evolution to strengthen learning on informative low-probability teacher tokens and Teacher Retirement to discard teacher outputs once the current policy can surpass them. On medical adaptation, OnePO achieves 67.2 on HealthBench (Total) with only 20K training samples, outperforming SFT+RL and pure RL by 2.7 and 7.4 points, respectively. We further scale OnePO to produce HuatuoGPT-3, an open-source medical LLM series whose 27B variant reaches 70.1 on HealthBench (Total) and 71.4 on HealthBench Professional, surpassing frontier models such as GPT-6 Astra. Models and code are available at https://github.com/FreedomIntelligence/HuatuoGPT-3.

cs.CL↗

PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents

Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static screenshots and interaction trajectories preserve realistic evidence but cannot generate new experience. We introduce PhoneWorld, a trace-grounded framework that converts such evidence into runnable, resettable, and verifiable Android environments. PhoneWorld induces a usage-weighted interaction skeleton from observed pages, transitions, and state-changing operations; translates it into a behavior-grounded app specification; realizes the specification through an autonomous build--inspect--repair loop; and synthesizes executable tasks with programmatic verifiers. The resulting suite spans 34 consumer-facing apps across 16 domains and supports an audited online benchmark, verified trajectory generation, and online RL through common reset and verification interfaces. Evaluations with diverse general and open-source GUI agents show that PhoneWorld supports reliable end-to-end online interaction and exposes capabilities complementary to AndroidWorld. Controlled SFT experiments further show that PhoneWorld trajectories complement AndroidWorld supervision, transfer across online and offline benchmarks, and become more effective as data volume and app coverage increase. Under a matched RL budget, combining PhoneWorld mock-app rollouts with real-app rollouts improves performance over real-app RL alone on both real-phone tasks and AndroidWorld. Together, these results demonstrate that trace-grounded executable abstraction can bridge realistic mobile behavior and scalable agent learning, turning limited real-app evidence into a growing supply of controllable and verifiable environments for training and evaluation.

cs.CL↗

How code helps different tasks? A decompositional lens on LLM post-training

Evaluating code data as a single corpus can obscure which types of code data benefit which models and downstream tasks. Effective data selection requires understanding both the benefits of individual categories and whether these benefits persist when categories are combined. We introduce a decompositional lens for studying these effects in LLM post-training. We first decompose an execution-verified code corpus into interpretable categories based on the computational patterns of its solutions. Through controlled fine-tuning experiments, we compare individual categories with a balanced mixture across instruction-tuned models on question answering, mathematics, and code generation. The resulting response maps reveal recurring gains in average question-answering performance, while the same category can improve one model or task and degrade another. The best-performing category also varies with the starting model and target task. We then compose compact mixtures guided by these results and examine whether benefits observed in individual categories persist under joint training. On selected model--task pairs, mixtures whose constituents each improve the target task outperform both their best constituent and full-corpus training while using roughly 10--15\% of the full corpus. These exploratory findings illustrate a \emph{less is more} pattern and highlight how the value of code data in post training depends on which categories are combined for which model and task.

cs.AI↗

HiMed: Incentivizing Hindi Reasoning in Medical LLMs

Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, their performance degrades sharply in Hindi, particularly on Indian systems of medicine. We argue that robust cross-lingual medical transfer requires Hindi reasoning. To this end, we introduce HiMed, a Hindi reasoning medical corpus and benchmark suite covering both Western and Indian medicine. We further propose HiMed-8B, a Hindi-form medical reasoning LLM, through the design of decaying scaffolding reward. Extensive experiments demonstrate improvement in Hindi medical reasoning performance and a reduction in the English-Hindi accuracy gap. Ablation studies validate the contribution of each training stage and reward component. All code, data, and weights are available

cs.CL↗

On Edge in the Dental Chair: Designing VR Support for Moments of Dental Anxiety

Dental anxiety can change as a procedure unfolds, yet dental virtual reality (VR) commonly provides continuous distraction or relaxation. We investigate how support can be coordinated with specific simulated dental events. Stakeholder interviews (N=36), participatory design with three returning dentists, and patient walkthroughs of a no-intervention prototype (N=12) informed five Anxiety Events and an intervention-module framework. Drawing on cognitive vulnerability and emotion regulation, we implemented a standardized event-contingent VR system with predefined event-module assignments and shared agency and safety controls. A randomized study (N=24) compared the intervention package with no-intervention VR. The adjusted intervention-minus-control difference averaged -12.83 VAS-A points across events (95% CI [-24.42, -1.70]). Physiological, behavioural, and qualitative measures contextualized participants' experiences. The findings inform timely, comprehensible support and reassuring social presence in simulated dental VR; they concern the complete package rather than individual modules or clinical effectiveness.

cs.HC↗

Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case Study

This paper proposes the Sinitic Romanization Ecosystem, a cross-lingual Sinitic romanization design framework with supporting digital infrastructure and a community-driven open-source workflow. The design framework addresses the lack of systematic cross-lingual romanization alignment among Sinitic languages through four design principles: phonetic correspondence for representing similar sounds with similar romanized symbols, historical-phonological correspondence for aligning cognate romanization strings, one-phoneme-one-symbol, and basic Latin-letter use, with a balancing consideration recognizing trade-offs among these principles. For the main paired case study, we develop CantRomZJ1 and MandRomZJ1, Cantonese and Mandarin romanization schemes following the design framework, respectively. We also develop schemes for several other Sinitic languages, including Meixian Hakka, Shanghai Wu, and Nanjing Jianghuai Mandarin, following the same design framework. To bring the romanization schemes into practical use, we develop open-source infrastructure for structured romanization storage, conversion, parsing, dictionary construction, and input-method generation. Finally, we evaluate the design framework through speech-to-romanization experiments based on Meta's Massively Multilingual Speech (MMS) fine-tuning. Compared with the Pinyin+Jyutping baseline, our MandRomZJ1+CantRomZJ1 condition reduces Cantonese WER and CER by 7.80% and 10.61%, respectively. These results suggest that cross-lingual romanization alignment can improve transfer in low-resource Sinitic speech technology.

cs.CL↗

Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction

The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether they can converse like humans. To tackle this, we conduct the first Turing test for S2S systems, collecting 2,968 human judgments on dialogues between 9 state-of-the-art S2S systems and 28 human participants. Our results deliver a clear finding: no existing evaluated S2S system passes the test, revealing a significant gap in human-likeness. To diagnose this failure, we develop a fine-grained taxonomy of 18 human-likeness dimensions and crowd-annotate our collected dialogues accordingly. Our analysis shows that the bottleneck is not semantic understanding but stems from paralinguistic features, emotional expressivity, and conversational persona. Furthermore, we find that off-the-shelf AI models perform unreliably as Turing test judges. In response, we propose an interpretable model that leverages the fine-grained human-likeness ratings and delivers accurate and transparent human-vs-machine discrimination, offering a powerful tool for automatic human-likeness evaluation. Our work establishes the first human-likeness evaluation for S2S systems and moves beyond binary outcomes to enable detailed diagnostic insights, paving the way for human-like improvements in conversational AI systems.

cs.AI↗

When Helpful Agents Cause Financial Harm: Evaluating LLM Agent Safety in Executable Economic Worlds

As LLM agents become increasingly capable of making consequential economic decisions, their safety under economic pressures remains poorly understood. We introduce EconSafeBench, the first benchmark for systematically evaluating the safety of LLM agents in executable economic environments. EconSafeBench contains 828 cases across five economic scenarios and four categories of safety violations. A key design is the matched evaluation of three sources of safety pressure, including explicit user requests, pressure from other actors, and pressure arising from the agent's own pursuit of a performance objective. We further evaluate safety at both static and dynamic scales through 30-period interactions with persistent memory and matched controls. Across eight LLMs, all evaluated models exhibit safety violations on the static benchmark, with overall violation rates ranging from 8.5% to 40.6%. We further find that violations can occur even without an explicit unsafe request, and that initially compliant agents may begin to violate as performance pressure increases over time. These findings highlight the need for stronger safety alignment and rigorous evaluation before LLM agents are deployed in high-stakes economic environments.

cs.CL↗

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model's realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.

cs.SD↗

DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis

Multiple instance learning (MIL) is widely used for weakly supervised whole slide image (WSI) analysis. However, under long-tailed distributions, MIL-based WSI analysis faces a nested dual long-tail: an inter-slide class long tail and an intra-slide long tail of instance-level discriminative evidence. The two long tails are coupled: tail classes have few training slides, while their limited diagnostic evidence is concentrated in a few patches and obscured by abundant within-bag redundancy. This coupling biases models toward head classes and degrades rare-class recognition. To address this, we propose DeCo-MIL for long-tailed WSI analysis, which jointly alleviates the nested dual long-tail through frequency-debiased counterfactual reasoning. For the inner long tail, DeCo-MIL clusters patches into tissue-morphology anchors, replaces each anchor with its matched normal prototype to perform a counterfactual intervention, and estimates its counterfactual contribution to the ground-truth class using class-frequency-corrected predictions. These contributions guide redundancy masking to preserve scarce discriminative instances. For the outer long tail, DeCo-MIL constructs anchor-stratified pseudo-bags from redundancy-reduced bags and combines tail-aware oversampling with consistency regularization, increasing effective supervision for tail classes while preserving tissue-morphology composition. Extensive experiments on three long-tailed WSI benchmarks demonstrate that DeCo-MIL achieves state-of-the-art performance in both tail-class recognition and overall classification.

cs.CV↗

RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning

Rare diseases represent one of the most challenging settings for clinical decision-making, where heterogeneous presentations, sparse evidence and limited expertise create persistent uncertainty throughout the care pathway. Although artificial intelligence could help, existing systems largely address isolated tasks, particularly diagnosis, and usually rely on downstream investigations rather than information available at initial presentation. Here we show that clinical AI performance under uncertainty can be improved not by scaling a single model, but by exploiting the diversity of multiple imperfect reasoning systems. Across heterogeneous large language models, we identify divergent reasoning trajectories with complementary error patterns and develop RareLens, which learns to reconcile these perspectives into actionable decisions across four stages of rare disease care: risk screening, diagnosis, treatment planning and prognosis prediction. Built on RarelensBench, a real-world dataset of 157,525 cases spanning all 33 Orphanet categories and more than 7,000 conditions, RareLens outperformed every frontier model tested, including GPT-5, DeepSeek-R1, Claude-3.7-Sonnet and Gemini-2.5-Pro, across all stages. It achieved an area under the curve of 0.917 for screening and top-1 accuracies of 65.5% and 89.8% for diagnosis and treatment. In an external evaluation involving 1,287 cases and 23 physicians, autonomous RareLens and physicians assisted by RareLens both outperformed unaided physicians, while demonstrating that effective human-AI collaboration requires more than simply providing model outputs. These findings establish divergent model reasoning as an exploitable source of information and suggest a general strategy for building AI systems that operate reliably under high clinical uncertainty.

cs.AI↗

From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models

Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the market and institutional mechanisms through which their interactions produce aggregate outcomes. This paper develops an implementation roadmap for building economic world models as generative engines in which heterogeneous agents act, interact, adapt, and co-evolve with markets and institutions, thereby producing economic dynamics from the inside. We organize EWM systems into a six-level capability ladder, from fixed rule-based agent worlds to adaptive and LLM-based agent worlds, self-evolving agents, evolving institutional worlds, and sim-to-real economic twins aligned with real observations. A systematic literature survey across these levels reveals that existing work remains concentrated in lower-level agent and simulation environments, while systems with self-evolving agents, endogenous institutions, persistent empirical alignment, and validated economic mechanisms remain rare. By translating the EWM agenda into an implementation blueprint, this paper aims to accelerate the development of the next generation of economic simulation environments that can serve as high-fidelity sandboxes for human decision-makers and as training, planning, evaluation, and safety substrates for AI agents. We release a curated paper list and related resources to support future research.

cs.AI↗

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment

As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on knowledge benchmarks, LLMs lack validated assessment for navigating ethical trade-offs in clinical decision-making where multiple valid solutions exist. Existing benchmarks lack systematic approaches to incorporate recognized philosophical frameworks and expert validation for ethical reasoning assessment. We introduce PrinciplismQA, a philosophy-grounded approach to assessing LLM clinical medical ethics alignment. Grounded in Principlism, our approach provides a systematic methodology for incorporating clinical ethics philosophy into LLM assessment design. PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning. Our expert-calibrated pipeline enables reproducible evaluation and models ethical biases. Evaluating recent models reveals significant ethical reasoning gaps despite high knowledge accuracy, demonstrating that knowledge-oriented training does not ensure clinical ethical alignment. PrinciplismQA provides a validated tool for assessing clinical AI deployment readiness. Our data and test scripts are fully released on https://github.com/FreedomIntelligence/PrinciplismQA.

cs.CL↗

MedEasy: Designing AI Standardized Patients for Clinical Consultation Training

AI standardized patients are becoming a setting for professional training in clinical consultation. This paper presents MedEasy, a multi-agent system that organizes virtual-patient practice through patient dialogue, clinical actions, decision submission, documentation, and feedback. We first conducted a formative study with 12 clinical-year medical students through interviews and three co-design workshops. The findings informed a staged workflow, structured case records, action-contingent findings, and trajectory-based review. We then conducted an evaluative user study with a separate cohort of 12 clinical-year medical students, with each participant completing two counterbalanced cases. Learners interpreted MedEasy as a connected consultation environment. They used patient responses, examination findings, available actions, and feedback together to judge whether the represented case remained coherent. They valued repeatable practice and recorded review, while questioning missing actions and feedback criteria. The paper contributes design implications for AI-supported professional training systems that use case-specific standards to connect situated practice.

cs.HC↗