Search arXiv⌕ Search

arXiv subjects

Siyuan Wang

Publications and source records attributed to Siyuan Wang.

At least 19 recordsLinked to original sources
arXiv2026

FISH Omics Format: a standard enabling FAIR chromatin tracing data sharing across repositories

In recent years, multiplexed Fluorescence In Situ Hybridization (FISH) or FISH-omics methods have rapidly expanded, enabling the quantification of chromatin organization in single cells, often in conjunction with measurements of RNAs and proteins. These approaches have deepened our understanding of how 3D chromosome architecture relates to transcriptional activity and cell states in health and disease. Despite these advances, results from Chromatin Tracing FISH-omics experiments remain challenging to share, reuse, and analyze due to the absence of standardized data exchange specifications. Building on the release of microscopy metadata standards, we introduce the FISH Omics Format-Chromatin Tracing (FOF-CT), a community-developed standard for processed results from diverse imaging modalities. We describe the FOF-CT file format and present a curated collection of datasets deposited in the 4D Nucleome Data Portal and the OME Image Data Resource (IDR). We also highlight their potential for reuse, integration, and modeling by outlining example analysis pipelines and illustrating biological insights enabled by standardized, FAIR-compliant Chromatin Tracing datasets. FOF-CT natively represents both ball-and-stick and volumetric Chromatin Tracing data, unifying the two modalities within a single, modular table-based architecture (FOF-bas-CT and FOF-vol-CT, respectively).

q-bio.OT↗
arXiv2026

HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol

Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an inherent communication trilemma: text-based methods are interpretable but verbose, while latent-space methods are efficient but opaque and limited to unidirectional workflows. Inspired by multi-channel communication theory, we propose HyLaT, a hybrid latent-text communication protocol that transmits elaborate cognitive signals through a latent channel for efficiency, while expressing concise critical signals in natural language to preserve interpretability and precision. We introduce a two-stage training framework combining single-agent hybrid generation learning and multi-agent interactive co-training, enabling agents to generate and interpret hybrid messages across multiple rounds of interaction. Experiments demonstrate that HyLaT reduces communication overhead significantly while maintaining competitive task performance, with strong generalization and robustness across diverse settings.

cs.CL↗
arXiv2026

RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation

Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal large language models (MLLMs) are increasingly used to judge these properties, yet their agreement with human judgments on embodied videos has not been systematically evaluated. To address this gap, we introduce RoboJudge-Bench, a benchmark for evaluating MLLMs as judges of embodied video generation. The benchmark measures two fundamental dimensions, Physical Adherence and Instruction Alignment, across 800 human-annotated videos from 8 source corpora and 10 video generators, spanning grippers, human hands, and dexterous hands. Experiments reveal uneven alignment between existing judges and human ratings: general-purpose MLLMs show lower agreement on physical adherence, while specialized video judges designed for general-domain physical reasoning do not consistently transfer to embodied scenarios. Motivated by these findings, we construct RoboJudge-Train, comprising 12K videos annotated with 25K human-verified scores and model-assisted rationales for Physical Adherence and Instruction Alignment. We fine-tune a 9B MLLM on this dataset with supervised learning followed by reinforcement learning, yielding RoboJudge-9B. Among the model judges evaluated on RoboJudge-Bench, RoboJudge-9B achieves the highest overall agreement, reaching a Pearson correlation of 0.719 with a statistically significant 0.089 gain over Gemini-3.7-Flash, the best-performing proprietary baseline in our evaluation. Training on RoboJudge-Train also yields gains on external benchmarks, including VideoPhy2 and Physion-Eval. We further use RoboJudge-9B as a downstream evaluator to benchmark video generation models according to Physical Adherence and Instruction Alignment.

cs.CV↗
arXiv2026

From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios

Recent multimodal large language models have advanced video understanding, but existing benchmarks mainly evaluate whether models can interpret observed visual content. In real-world scenarios, assistants must additionally anticipate what assistance is needed and decide when to provide it. To address this gap, we introduce \textsc{P$^3$IBench}, a benchmark for proactive video understanding in real-life streaming scenarios. It evaluates three complementary capabilities: daily perception, risk prediction and intervention. We benchmark 12 representative open-source and proprietary video-language models, including streaming and adapted non-streaming systems. Our evaluation shows that current models struggle to make well-calibrated response decisions. Finally, we construct additional proactive training data and train \textsc{P$^3$I-Assistant-4B}, achieving improvements on several tasks, though gains remain uneven across capabilities. Together, these findings show that effective proactive assistance requires not only visual understanding, but also precise response timing and appropriate restraint.

cs.LG↗
arXiv2026

ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking

Large reasoning models solve complex problems through long chains of thought, in which prior work has documented failure modes such as overthinking, underthinking, and unsupported deductions. Existing methods detect these failures from local signals: textual similarity to nearby steps, switch tokens, or an LLM's judgment of a step's correctness. However, what a step contributes to the solution depends on the state that earlier steps have established, so identifying failures requires a global view that tracks that state across the trajectory. Therefore, we propose ARBOR, a reasoning-failure attribution framework that represents each trajectory as a tree of reasoning states, built as each step creates, verifies, prunes, or revisits a state, and attributes each failure to a relation between a step and the state preceding it. Using ARBOR, we refine the three failure modes into distinct subtypes that harm reasoning through different mechanisms and at different costs. We find that the tree state ARBOR maintains before a step separates failure steps from the at-risk steps at which the failure did not occur. We discuss how ARBOR integrates with existing mitigations at inference time and in training data. Code, data and interactive examples are available at https://inklab.usc.edu/ARBOR.

cs.CL↗
arXiv2026

General Decision Models: Benchmarking and Insights Beyond Jev

General decision models, such as Jev, have recently emerged as efficient alternatives to LLMs for structured judgment and selection. But what kinds of decisions can these models reliably make, and how does their behavior change when individual decisions are composed into larger systems? To study this, we introduce JEVal, a bilingual benchmark comprising 11,257 instances from 36 datasets across 10 application domains, and evaluate 25 model configurations spanning general decision models and generative LLMs. Our results show that (1) general decision models are most competitive when decisions can be resolved from available evidence, but weaken when they require specialist knowledge or faithful uncertainty estimation: they can often identify the most likely outcome while substantially overstating its probability. (2) In more dynamic and realistic systems involving long-horizon, multi-step interactions, the advantages of fast local decision making are offset by reliability failures at the system level. on $τ$-bench, faster local decisions reduce median episode time but lower task success as decision errors accumulate over long trajectories. (3) In large-scale social simulation, decision models approach strong generative LLMs on individual response prediction at substantially lower inference cost, yet remain weaker in user profiling and exhibit larger aggregate estimation errors and systematic bias. Finally, we propose SII-Decision-4B and SII-Decision-27B, which internalize an open-weight LLM's own reasoning into a single-pass first-token decision through Reasoning-to-Readout Self-Distillation, with SII-Decision-27B performing on par with Jev on JEVal while answering a typical query in about 0.1 s.

cs.CL↗
arXiv2026

What Makes Recurrence Effective in Looped Language Models?

Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters. However, it remains unclear when additional recurrence is beneficial and how architectural choices affect its effectiveness. Through controlled experiments, we systematically examine (1) when recurrence helps, (2) where it should be applied, and (3) how its conditioning affects performance. Our evaluation covers inference budgets below, within, and beyond the training horizon under knowledge and reasoning tasks. (1) We find that recurrence can improve reasoning beyond the training horizon while degrading knowledge performance, but harder reasoning instances do not consistently benefit more. (2) Performance also depends on how distinct layers and recurrent iterations are allocated, showing that effective depth alone is insufficient to predict behavior. Non-recurrent output layers improve robustness to under-unrolling, while the preferred placement of input and output layers varies with inference budget. (3) Finally, we find that conventional initial-state injection offers limited robustness to varying recurrence depth. We therefore propose history-state injection as an alternative, and show that channel-wise history-state injection combined with timestep conditioning offers a low-cost and more effective design, better preserving knowledge under extended unrolling while improving robustness across inference budgets. Overall, our results clarify when recurrent computation helps, where it fails, and offer practical guidelines for designing LoopLMs across variable inference budgets.

cs.LG↗
arXiv2026

ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments

Language model agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods face a performance-efficiency tradeoff: they either rigidly decouple exploration and execution or interleave them without coordination. We argue that the key lies not in whether to decouple or interleave them, but in how to coordinate them across granularities. We introduce ParaAct, a structured parallel-action loop that combines phase-level Exploration $\rightleftharpoons$ Execution with action-level parallelism. To learn this loop, ParaAgent combines multi-agent cold-start demonstrations with reinforcement learning under multi-level advantage decoupling, making planning structure explicit and supervising it with step-, phase-, and trajectory-level rewards. Learning is supported by our ToolEnv, a scalable simulator grounded in 50,011 realistic tool interfaces. On two open-world tool benchmarks, ParaAgent-4B achieves the best average success among all baselines, including GPT-4.1 systems, with the largest gains on multi-tool tasks. Behavioral analyses show that these gains stem from this action organization, highlighting its importance for capable and efficient open-world agents.

cs.AI↗
arXiv2026

AI-driven ionic liquid discovery with unified chemical intelligence

The rational discovery of functional solvents remains challenging because macroscopic solvent behaviors emerge from complex many-body interactions across vast chemical spaces. Ionic Liquids (ILs) constitute one of the most chemically diverse solvent families, yet their exceptional structural tunability remains only partially explored owing to the limitations of existing experimental and computational approaches. Here we introduce AIonopedia, a large-language-model-orchestrated agentic framework for IL research. Built around a domain-specific multimodal foundation model, it integrates information retrieval, chemical reasoning and autonomous tool execution within a unified architecture. Pretrained on large-scale unlabeled corpora and fine-tuned using over 80,000 curated measurements, AIonopedia learns expressive joint representations of multicomponent ionic systems, enabling accurate prediction across diverse physicochemical properties. Through a series of literature-grounded evaluations, AIonopedia exhibits robust out-of-distribution generalization, while many-body-expansion-based analysis provides physically grounded explanations of structure-property relationships. By coupling molecular screening and optimization with wet-lab validation in a closed-loop workflow, AIonopedia identifies high-performance ILs and reveals transferable design principles for the capture of various volatile organic compounds. This work establishes an end-to-end AI-driven paradigm for understanding and exploring complex ionic systems, demonstrating the promise of chemically specialized foundation models as a generalizable strategy for scientific discovery.

cs.AI↗
arXiv2026

RL Starts before RL: On Policy Distillation for Better Reinforcement Learning

Reinforcement learning (RL) improves reasoning, but its performance depends on the policy from which training begins. We study on-policy distillation (OPD) as a preparation stage for RL and ask whether its benefits extend beyond improvements in the distilled model's initial accuracy. Under shared RL settings, students initialized with OPD reach higher final performance than those trained with direct RL or supervised fine-tuning followed by RL. This advantage can emerge even when OPD produces little immediate improvement in accuracy. Pre-RL Pass@k does not fully explain the benefit: similar or even higher values do not necessarily lead to better performance after RL. Behavioral analyses point to alignment with the teacher's distribution beyond top-1 agreement as a possible explanation. Such alignment may favor higher-quality reasoning paths while retaining alternatives that RL can further refine using outcome feedback. We further examine how trajectory sources and divergence objectives affect the value of distillation for subsequent RL. Standard reverse-KL OPD performs better before RL, but forward-KL OPD overtakes it afterward. Student rollouts outperform teacher rollouts under both objectives before and after RL. These findings highlight the importance of both objective choice and the states receiving supervision for subsequent RL. Our results support OPD as preparation for RL and favor forward KL when OPD is followed by RL in our comparison.

cs.LG↗
arXiv2026

SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm

Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by acting as silicon samples that unite agent-based modeling with real behavioral data. Existing platforms verify collective behavior, align simulated populations with real societies in cross-sections, and employ autonomous agents for the research process. However, two social science requirements remain without systematic support: intervention in the content of a simulation and the researcher's control over the process that produces it. We present SocioVerse2, which extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure. The longitudinal simulation loop simulates the target population with evolving environments and forks counterfactual branches via interventions. The controllable research loop takes the study itself as an editable state and updates state versions via controllable editing. The social science agentic infrastructure carries both loops through composable skills with researcher checkpoints, a population service over five persona pools, and an environment service over 21 real-world signal sources with point-in-time guarantees. We validate SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff. With the human-AI co-evolutionary paradigm, these cases go beyond system demonstrations to become substantive studies that investigate frontier questions in their respective disciplines. Code, data services, and a workbench are released as open-source resources.

cs.CL↗
arXiv2026

MIRA-PRM: Mission-Informed Reusable Roadmap Planning for Mobile Gas-Sensing Inspection

Mobile gas-sensing inspection requires a mobile platform to reliably reach ordered sampling poses. We present MIRA-PRM, a mission-informed probabilistic roadmap that combines geometry-, mission-flow-, and inspection-conditioned sampling with locally adaptive connectivity and evidence-gated refinement. Eight development campaigns comprising 142,448 planner runs evaluated mission scaling, repeated-query adaptation, finite node budgets, target distributions, local map repair, ablation, cross-family comparison, and parameter sensitivity. MIRA-PRM maintained 100% seed-level success as ordered targets increased from two to eight, and achieved 97.67% seed-level success under a 40-node ceiling, compared with 67.17% for PRM and 86.50% for PRM*. Local repair reduced event time by 79.9-81.9% and node additions by 90.8-94.3% relative to rebuilding. On a separate frozen holdout of 12 maps, 48 ordered missions, and three seeds per map-mission unit, MIRA-PRM produced 96/144 validated successes, versus 82/144 for PRM, 89/144 for PRM*, and 70/144 for LE-HG-PRM. On paired common-success runs, MIRA-PRM reduced wall time by 16.89% relative to PRM* and 81.01% relative to LE-HG-PRM, but was 52.23% slower than PRM; paths were 0.54-1.86% longer. All validated paths passed independent full-segment checks and clearance non-inferiority. The results support a reliability-oriented trade-off in structured simulations and motivate external-map and physical mobile-sensing validation.

cs.RO↗
arXiv2026

RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases

Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions. Search generally helps, but all four diagnostic models perform worse than an exact-count exponentially weighted moving average (EWMA) baseline in compositional accuracy. We identify two linked bottlenecks. Under cumulative-history access, State carry-forward outperforms direct Forecast for all four diagnostic models; frozen-evidence replay links a shared component of this reversal to Forecast-oriented policies retrieving a smaller share of recent evidence. Even with exact historical activity, future-specific updating remains limited, with only GPT-5.5 plus reopened Search slightly surpassing EWMA. Fine-tuning on realised outcomes improves Qwen3-4B's forecast Spearman correlation by 0.105 on held-out fields at later origins, with gains also on change-rich episodes.

cs.AI↗
arXiv2026

Ultra-Short-Term Photovoltaic Ramp Forecasting via Physics-Guided Generative Sky Video Prediction

Minute-scale photovoltaic (PV) ramps caused by rapidly evolving cloud occlusion pose challenges to short-timescale power balancing and require reliable advance warning. This paper develops an event-oriented ultra-short-term PV forecasting framework that predicts future cloud evolution as an intermediate representation linking sky observations to PV output. PhyDiffNet combines physics-informed cloud-motion modeling with generative video prediction, while RaPVFormer integrates observed and predicted sky states, sun-location information, and historical PV measurements to forecast PV trajectories and ramp events up to 16 minutes ahead. Evaluation on the SKIPP'D dataset shows that the proposed framework achieves a Critical Success Index of 96.2\% for ramps beginning 1--4 minutes ahead and retains 84.9\% for those beginning 13--16 minutes ahead, outperforming all deployable baselines across the evaluated lead-time intervals. At a validation-calibrated 95\% reliability target, it reduces the required fast upward reserve margin by 34.2\% relative to the Persistence Model and by 11.6\% relative to the strongest deployable baseline under the adopted reserve metric. These results show that explicit future-cloud prediction improves advance warning of PV ramps and translates forecasting gains into lower short-timescale balancing margins under a common reliability target.

eess.SY↗
arXiv2026

PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization

Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a codeword at each level and passing a residual to the next. We view this process as progressive commonality removal: each token captures a component shared within its group, while later tokens should model the remaining differences. This view reveals three limitations: a corpus-wide shared component can consume first-level capacity, hard assignment ignores graded similarities to nearby codewords, and full-codeword subtraction can leave variation along the selected-codeword direction in the next residual. We therefore develop our solution in the post-hoc setting, where residual construction is not constrained by input reconstruction. Specifically, we propose PRQ-KMeans, which removes the global-mean component, refines centroids with Top-k similarity-weighted updates, and replaces full-codeword subtraction with a projection residual that removes each representation's selected-centroid component. Experiments on a large-scale industrial search dataset and four public recommendation benchmarks show that PRQ-KMeans achieves the strongest overall performance among the evaluated tokenizers, including gains of up to 7.4% in HitRate and 11.8% in MRR on the industrial dataset.

cs.LG↗
arXiv2026

SciTrue: Reliable Scientific Claim Validation with Frontier and Open Language Models at the NTCIR SciClaimEval Task

We describe the SciTrue team's participation in both subtasks of the NTCIR-19 SciClaimEval task~\cite{sciclaimeval}, which asks systems to verify scientific claims against the tables and figures of a paper. Rather than tuning a single model, we benchmark eleven frontier and open multimodal models under one honest, per-sample protocol and combine them with light, transparent post-processing. On the official, blind test leaderboard (Section~\ref{sec:results}), SciTrue placed first by a clear margin in three of the four evidence-category/subtask combinations, and tied for first on the primary metric in the fourth. Three findings explain the result. First, strong instruction-tuned models are already competitive: Claude Opus~4.8 and Gemma-4-31B each exceed the strongest public baseline (o4-mini), and GPT-5.5 and Claude Fable~5 lead both subtasks (97.7 on Subtask~2). Second, the task's pairing structure is the largest lever: a \emph{leak-free pair prior} that recovers the Supported/Refuted pairing from the claim text alone (a visible field) and assigns Supported to the higher-confidence evidence raises Subtask-1 pair-accuracy from 72.2 to 93.5, far more than any model swap or ensemble weighting. Third, a case-by-case audit finds that most residual errors are visually-undetectable label-mapping swaps or dataset label noise, so measured accuracy understates the true ability and the fixable-by-modeling headroom is small. Controlled fine-tuning, distillation, and agentic consistency-checking support the same conclusions, and we document throughout a measurement leak---label information reaching a system through the packaging of the data rather than its content---in which the released file ordering encodes the label, including one instance that briefly misled our own pipeline.

cs.AI↗
arXiv2026

GeoGR: Enabling Spatio-Temporal Aware Industrial-scale Generative POI Recommendations

Next Point-of-Interest (POI) prediction is a fundamental task in location-based services (LBS), especially critical for large-scale navigation platforms such as AMAP that serve billions of users in diverse lifestyle scenarios. Although recent POI recommendation approaches based on SIDs have achieved promising performance, they struggle in complex, sparse real-world environments due to two key limitations: (1) inadequate modeling of high-quality SIDs that capture cross-category spatio-temporal collaborative relationships, and (2) poor alignment between large language models (LLMs) and the POI recommendation task. To this end, we propose GeoGR, a geographic generative recommendation framework tailored for navigation-based LBS like AMAP, which perceives changes in users' contextual states and enables spatio-temporal aware POI recommendation. GeoGR features a two-stage design: (i) a geo-aware SID tokenization pipeline that explicitly learns spatio-temporal collaborative semantic representations via geographically constrained co-visited POI pairs, contrastive semantic representation learning, and iterative refinement; and (ii) a multi-stage LLM training strategy that aligns non-native SID tokens through continued pre-training with multiple prompt templates and enables autoregressive POI generation via supervised fine-tuning. Extensive experiments on multiple real-world datasets demonstrate GeoGR superiority over state-of-the-art baselines. Moreover, the deployment on the large-scale AMAP platform over three months, serving millions of users and delivering significant online gains of +2.91% in WINRATE and +5.55% in PV_CTR, confirms its practical effectiveness and scalability in production.

cs.IR↗
arXiv2026

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.

cs.MA↗