arXiv subjects

Yizhan Li

Publications and source records attributed to Yizhan Li.

7 recordsLinked to original sources

arXiv2026

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

Reacting to sudden physical hazards (catching a slipping plate, dodging a falling knife) is both a meaningful test of embodied intelligence and a hard requirement for deploying multimodal large language models (MLLMs) as the decision coreof household robots. Existing evaluations, however, probe intuitive physics passively through question answering over videos, or target deliberate, long-horizon tasks such as navigation and rearrangement; none measure whether a model can turn physical understanding into immediate, safety-critical action. We introduce ReactHuman, the first physics-grounded benchmark for human-like reactive decision-making, in which the evaluated MLLM acts as the brain of a simulated humanoid facing sudden household hazards; it spans 17 event families and over 1,000 bit-for-bit reproducible scenes with exact, annotation-free ground truth derived from 240 Hz rigid-body simulation, including adversarial objects whose appearance contradicts their physics (a foam anvil, a steel apple). We further design a five-metric suite that scores each reaction along three axes: reasonable, safe, and physically grounded. We physically execute every committed plan so that decisions have observable consequences. With this harness we evaluate seven representative MLLMs. Results show that reactive safety is far from solved: models mishandle roughly one hazard in three, act from fixed dispositions rather than the observed scene, trust appearance over motion, and miss interception points at meter scale even when the chosen action is correct; none of these failures shrink with model scale. ReactHuman thus offers both a fine-grained diagnosis and a scalable training signal toward physically grounded, safety-aware embodied agents. The benchmark can be found here: https://huggingface.co/datasets/Alan123/reacthuman-benchmark-scaled

cs.RO↗

arXiv2026

Co-leading Teams Drive Scientific Novelty in Large-scale Research Infrastructures

Large-scale research infrastructures (LSRIs) have become the engine of modern scientific discovery. While these big machines predominantly operate under a user-oriented model where external teams conduct research with support from in-house researchers, the structural integration of staff scientists into user teams and its association with scientific novelty remains unclear. By leveraging a dataset of 273,109 publications across 76 global LSRIs and applying a hybrid machine-learning framework to classify papers into three collaboration patterns: external user only, staff participating, and staff co-leading, we find a distinct novelty premium for external teams that formally integrate staff as co-authors, especially when staff scientists play co-leading rather than participating roles. Further, the premium peaks at a relatively balanced user-staff team composition, potentially due to an "epistemic lock-in" by either party. Crucially, we find that the ideal collaboration architecture evolves with user experience: while newcomers can obtain a large novelty premium from mere staff participation, experienced users only benefit from staff co-leading teams. This result suggests a "knowledge saturation effect" for which a deeper intellectual partnership is needed to sustain novelty. By revealing how user-staff collaboration structure drives scientific creativity, our study offers practical policy implications for the strategic management and intervention of LSRIs in the era of human-machine collaboration.

cs.DL↗

arXiv2026

Scientific tools and Innovation: Big Science Facilities Yield More Novel and Interdisciplinary Knowledge

Scientific tools dictate the boundaries of human knowledge, serving as the foundation for perceptions and explorations. In the era of Big Science, science are increasingly dependent on advanced analytical technologies and experimental platforms. Over the past decades, national and supranational entities have invested massive financial resources, collaborative networks, and collective intelligence to construct Big Science Facilities (BSFs) aimed at generating cutting edge knowledge. However, empirical evaluations of these machines actual performance in driving scientific innovation remain scarce. To address this gap, we collected 310,086 publications from 88 global BSFs and constructed a matched control dataset of approximately 3 million publications sharing the same last authors. Our analysis reveals that the utilization of BSFs has expanded significantly since 1950s. Crucially, publications supported by these facilities exhibit higher recombinant novelty and interdisciplinary integration. Furthermore, this improvement is most pronounced in non physical sciences domains traditionally peripheral to BSFs core focus indicating the emergence of a powerful intra facility knowledge spillover effect. By enriching the Facilitymetrics framework, our findings provide empirical evidence that BSFs act as vital engines for scientific discovery, offering policymakers essential metrics to justify infrastructural investments, while prompting the science of science community to reassess the profound impact of scientific tools on knowledge production

cs.DL↗

arXiv2026

Towards Agentic Intelligence for Materials Science

The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan, act, and learn across the full discovery loop. This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining, through domain adaptation and instruction tuning, to goal-conditioned agents interfacing with simulation and experimental platforms. Unlike prior reviews, we treat the entire process as an end-to-end system to be optimized for tangible discovery outcomes rather than proxy benchmarks. This perspective allows us to trace how upstream design choices-such as data curation and training objectives-can be aligned with downstream experimental success through effective credit assignment. To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science. We then analyze the field through two focused lenses: From the AI perspective, the survey details LLM strengths in pattern recognition, predictive analytics, and natural language processing for literature mining, materials characterization, and property prediction; from the materials science perspective, it highlights applications in materials design, process optimization, and the acceleration of computational workflows via integration with external tools (e.g., DFT, robotic labs). Finally, we contrast passive, reactive approaches with agentic design, cataloging current contributions while motivating systems that pursue long-horizon goals with autonomy, memory, and tool use. This survey charts a practical roadmap towards autonomous, safety-aware LLM agents aimed at discovering novel and useful materials.

cond-mat.mtrl-sci↗

arXiv2026

M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints

Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce \textbf{M olGen}, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.

cs.AI↗

arXiv2025

Improving Clinical Note Generation from Complex Doctor-Patient Conversation

Writing clinical notes and documenting medical exams is a critical task for healthcare professionals, serving as a vital component of patient care documentation. However, manually writing these notes is time-consuming and can impact the amount of time clinicians can spend on direct patient interaction and other tasks. Consequently, the development of automated clinical note generation systems has emerged as a clinically meaningful area of research within AI for health. In this paper, we present three key contributions to the field of clinical note generation using large language models (LLMs). First, we introduce CliniKnote, a comprehensive dataset consisting of 1,200 complex doctor-patient conversations paired with their full clinical notes. This dataset, created and curated by medical experts with the help of modern neural networks, provides a valuable resource for training and evaluating models in clinical note generation tasks. Second, we propose the K-SOAP (Keyword, Subjective, Objective, Assessment, and Plan) note format, which enhances traditional SOAP~\cite{podder2023soap} (Subjective, Objective, Assessment, and Plan) notes by adding a keyword section at the top, allowing for quick identification of essential information. Third, we develop an automatic pipeline to generate K-SOAP notes from doctor-patient conversations and benchmark various modern LLMs using various metrics. Our results demonstrate significant improvements in efficiency and performance compared to standard LLM finetuning methods.

cs.CL↗

arXiv2025

Seeing Beyond Words: MatVQA for Challenging Visual-Scientific Reasoning in Materials Science

The emergence of Multimodal Large Language Models (MLLMs) that integrate vision and language modalities has unlocked new potentials for scientific reasoning, outperforming prior benchmarks in both natural language and coding domains. Current materials science evaluation datasets such as MaScQA and SciQA remain largely text-based and fail to capture the visual and research-level analytic complexity required in materials discovery and design. We introduce MatVQA, a scalable benchmark specifically designed to address this gap. Generated via an automated pipeline, MArxivAgent, from recent materials literature, MatVQA features 1325 questions across four critical structure-property-performance (SPP) reasoning tasks. Uniquely, MatVQA employs an iterative process to eliminate textual shortcuts, compelling MLLMs to perform fine-grained, low-level visual analysis of material imagery (e.g., microscopy, diffraction patterns) integrated with multi-step scientific reasoning. Benchmarking 17 open- and closed-source MLLMs on MatVQA reveals substantial gaps in current multimodal reasoning capabilities. MatVQA benchmark data, along with evaluation code, is publicly available in \href{https://anonymous.4open.science/r/matvqa-1E01}{https://anonymous.4open.science/r/matvqa-1E01/README.md} to catalyze further research in applying MLLMs to complex materials science problems.

cs.CE↗