Qianggang Ding

People often tackle difficult problems by thinking more deeply or exploring more possibilities. Similarly, recursive reasoners, which reason… (voir plus) by repeatedly applying a learned update rule to latent states, can also scale inference through more updates (depth) or additional trajectories generated by perturbing latent states (width). When people hit a dead end in their thinking, they may step back and approach the problem from a fresh angle. However, neither depth scaling nor perturbation-based width scaling of recursive reasoners can reliably achieve this: both may converge to incorrect attractors. To address this, we propose to explore diverse reasoning traces by applying different update maps to the same latent state, without any additional training. We realize this idea through \emph{Input-Conditioned Search (ICS)}, which searches over input conditions to induce alternative update maps from the pretrained reasoner. Across six reasoning tasks, ICS achieves the highest mean accuracy, while requiring up to two orders of magnitude fewer model FLOPs than the evaluated scaling baselines. Controlled experiments confirm that ICS can redirect trajectories from the same state. Our theoretical analysis and rigorous numerical verification also confirm that ICS can locally eliminate incorrect attracting fixed points. Together, these findings establish ICS as an effective axis for efficient test-time scaling and motivate further research on shaping recursive reasoning during training and at test time.

2026-10-12

arXiv (prépublication)

ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

Xingyao Wang

Rui Feng

Zhibin Wang

Feixiang Yao

Kelong Mao

Hao Sun

Zhiyao Luo

Jiankai Tang

Lei Li

Jiadong Guo

Minheng Ni

Weicong Lin

Chenxi Yang

Hongxiang Gao

Zhenghua Chen

Yang Bai

Min Wu

Jun Cheng

Huazhu Fu … (voir 2 de plus)

Dacheng Tao

After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Ye… (voir plus)t neither explains whether the person forgot, is confused, has side effects, or deliberately refused, nor what support is appropriate. This reveals a structural gap in Agentic AI: Digital Agents primarily transform software states, while Embodied Agents transform physical states; neither makes a person's evolving state and agency the primary object of modeling, intervention, and evaluation. We introduce Combodied Agents, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time, using software tools, sensors, wearables, robots, and human services as action channels rather than end goals. We unify fragmented capabilities across personal assistants, health agents, AI companions, and adaptive human--AI systems into a closed loop: event-based multimodal perception reconstructs meaningful personal events; longitudinal, correctable memory provides temporal context; Personal World Models estimate future personal states and outcomes under alternative decisions and interventions; and an admissible intervention policy selects proportionate support under consent, uncertainty, safety, reversibility, and user control. Feedback from the person and environment updates the loop. Rather than requiring an exhaustive Human Digital Twin, the framework uses purpose-bounded, uncertainty-aware, user-correctable representations. We organize the design space by human-state targets, relational contexts, and agent roles, and propose scenario-centered evaluation, agency-preservation metrics, benchmark requirements, edge-native personal models, and governance directions. Combodied Agents shift Agentic AI from external task completion toward sustained human benefit.

2026-08-10

arXiv (prépublication)

TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

Haochen Shi

Luis Castejón Lozano

Miguel Conner

Juan Abia

Luis Gallego-Ledesma

Joshua Fellowes

Gerard Conangla Planes

Adam Elwood

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies s… (voir plus)ymbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable \texttt{UP}/\texttt{DOWN} verdicts with human-readable paths connecting text and structure. On an S\&P~500 benchmark, the method achieves 55.1\% accuracy, 55.7\% precision, 71.5\% recall, and 60.8\% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.

2026-03-11

arXiv (prépublication)

Predicting viral respiratory tract infections using wearable biosensor monitoring during 3-minute constant rate stair stepping tests

Oussama Jlassi

Amir Hadid

Emily G. McDonald

Christopher Phillipp

Audrey Trottier

Matthew Pellan Cheng

Jesse Papenburg

Michael Libman

Dennis Jensen

Philippe C. Dixon

Background Viral Respiratory Tract Infections (VRTIs) are a major public health threat. Early detection and preventive measures are key to c… (voir plus)ontrolling their spread. Current machine learning approaches often depend on symptom onset, costly equipment, trained personnel, and slow results. This study aims to evaluate whether a machine learning algorithm using physiological data from wearable biosensors during a constant-rate stair-stepping task (3-min test, 2-min recovery) can predict inflammation levels, and to identify the most predictive indicators of VRTI. Methods 55 Healthy participants (27 males and 28 females) aged 18–59 years, were recruited and inoculated with a live influenza vaccine to induce an immune response, assessed via changes in circulating inflammatory biomarkers. Physiological markers, including breathing rate and heart rate, during a series of clinically controlled stair tests, were monitored by a wearable biosensor. These data were collected to develop a prediction model using gradient-boosting machine learning algorithms combined with hyperparameter tuning and a leave-one-subject-out method to train the models. Results The study developed a predictive model that accurately estimates inflammation levels in individuals. Features from heart rate variability (HRV) showed the greatest potential, with 70% sensitivity and 77% specificity, and physiological markers from controlled stair tests correlated with VRTI-related inflammatory responses. Impact The prediction model linked to stair-stepping tests offers clinicians and the public a tool for self-monitoring and early intervention. Using machine learning and physiological markers, especially HRV features, it can help guide timely treatments and reduce the impact of future outbreaks.

2026-02-12

Frontiers in Sensors (publié)

Towards Agentic Intelligence for Materials Science

Huan Zhang

Yizhan Li

Wenhao Huang

Ziyu Hou

Yu Song

Xuye Liu

Jinya Jiang

Leonard R. MacGillivray

Teruyasu Mizoguchi

Tianshu Yu

Lizi Liao

Yuyu Luo

Yu Rong

Jia LI

Ying Diao

Heng Ji … (voir 1 de plus)

The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in d… (voir plus)iscovery 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.

2025-12-31

arXiv (prépublication)

MatExpert: Decomposing Materials Discovery by Mimicking Human Experts

Santiago Miret

Material discovery is a critical research area with profound implications for various industries. In this work, we introduce MatExpert, a no… (voir plus)vel framework that leverages Large Language Models (LLMs) and contrastive learning to accelerate the discovery and design of new solid-state materials. Inspired by the workflow of human materials design experts, our approach integrates three key stages: retrieval, transition, and generation. First, in the retrieval stage, MatExpert identifies an existing material that closely matches the desired criteria. Second, in the transition stage, MatExpert outlines the necessary modifications to transform this material formulation to meet specific requirements outlined by the initial user query. Third, in the generation state, MatExpert performs detailed computations and structural generation to create new materials based on the provided information. Our experimental results demonstrate that MatExpert outperforms state-of-the-art methods in material generation tasks, achieving superior performance across various metrics including validity, distribution, and stability. As such, MatExpert represents a meaningful advancement in computational material discovery using langauge-based generative models.

2025-04-22

International Conference on Learning Representations (Accept (Poster))

openreview.net

DASFormer: self-supervised pretraining for earthquake monitoring

Zhichao Shen

Weiqiang Zhu

Earthquake monitoring is a fundamental task to unravel the underlying physics of earthquakes and mitigate associated hazards for public safe… (voir plus)ty. Distributed acoustic sensing, or DAS, which transforms pre-existing telecommunication cables into ultra-dense seismic networks, offers a cost-effective and scalable solution for next-generation earthquake monitoring. However, current approaches for earthquake monitoring like PhaseNet and PhaseNet-2 primarily rely on supervised learning, while manually labeled DAS data is quite limited and it is difficult to obtain more annotated datasets. In this paper, we present DASFormer, a novel self-supervised pretraining technique on DAS data with a coarse-to-fine framework that models spatial-temporal signal correlation. We treat earthquake monitoring as an anomaly detection task and demonstrate DASFormer can be directly utilized as a seismic phase detector. Experimental results demonstrate that DASFormer is effective in terms of several evaluation metrics and outperforms state-of-the-art time-series forecasting, anomaly detection, and foundation models on the unsupervised seismic detection task. We also demonstrate the potential of fine-tuning DASFormer to downstream tasks through case studies.

2024-12-31

Visual Intelligence (publié)