Searcharxiv⌕ Search

arXiv subjects

Minghao Guo

Publications and source records attributed to Minghao Guo.

At least 19 recordsLinked to original sources
arXiv2026

Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents

Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon exploration and rarely test whether agents can sustain long, dependency-heavy research processes. We introduce Mr.LHDR (Multimodal real-world Long-Horizon Deep Research), a benchmark for evaluating real-world deep research over long, irreducible chains of interdependent evidence across eight categories. Each question is constructed from a hidden Node-Relation graph and requires an average of 12.1 necessary intermediate conclusions with a mean dependency depth of 10.4 before reaching a short, unique, and verifiable answer. Questions incorporate multimodal evidence, including images, maps, PDFs, logos, charts, tables, and video frames, with at least one non-text element that changes the reasoning state. Mr.LHDR evaluates both final answers and the correctness of intermediate conclusions under annotated dependencies. We evaluate general models, deep research systems, and agent frameworks using Overall Accuracy (OA), Strict Accuracy (SA), Checklist Score (CS), and Dependency-Aware Checklist Score (DACS). Results show that even the strongest system achieves only 43.1% OA and 34.3% SA, indicating that final-answer accuracy substantially overestimates complete research success. Removing images reduces DACS by 12.6 points, demonstrating the importance of multimodal evidence, while SA consistently declines as reasoning chains become longer. These findings reveal sustained, dependency-consistent evidence integration, rather than isolated fact retrieval, as a key bottleneck for current deep research agents.

cs.AI↗
arXiv2026

Agents in the Large: Perception-Centered Architecture for Persistent Agents

Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.

cs.CL↗
arXiv2026

Mapping gas accretion and stellar kinematics to sub-kiloparsec scales in NGC 4696 with JWST/NIRSpec

We present JWST/NIRSpec IFU spectroscopy of the central $618\times618$ pc$^2$ ($\sim3''\times3''$) of NGC 4696, the BCG in the Centaurus cluster. Leveraging the $\sim0.1''$ ($20.6$ pc) pixel size of JWST, we resolve a compact circumnuclear rotating disk (radius of $\sim120$ pc) traced by Pa$\alpha$ and H$_2$ 1$-$0 S(1) emission, which allows a reassessment of the AGN position based on the kinematic centre of this disk. A central Pa$\alpha$ velocity dispersion reaching $\sigma\sim449$ km s$^{-1}$ implies a SMBH mass of $\sim10^9$ M$_\odot$, corresponding to a sphere of influence of $r_\mathrm{inf}\sim60$ pc, resolved by our observations. Position-velocity diagrams reveal an increase from $\sim-200$ to $\sim600$ km s$^{-1}$ on scales of $\sim150$ pc (a gradient of $4.7$ km s$^{-1}$ pc$^{-1}$) and an accretion rate of $\sim18$ M$_\odot$ yr$^{-1}$ feeding the CND. The Pa$\alpha$ emission shows a double-component in the core, with a high-dispersion redshifted component reaching $\sigma\sim600$ km s$^{-1}$. In contrast, MUSE H$\alpha$ observations covering the $\sim10$ kpc-scale filamentary structure recover only weak velocity gradients ($\lesssim150$ km s$^{-1}$) within $\sim300\times300$ pc$^2$ and do not resolve the disk due to larger PSFs and pixel sizes. ALMA CO(2-1) data reveal only compact molecular clumps within a $\sim410\times410$ pc$^2$ region, with no extended counterpart to the structures traced by Pa$\alpha$ and H$_2$ 1$-$0 S(1). Stellar kinematics show a smooth velocity field and broad dispersion profile, clearly decoupled from both the multiphase gas and the hot ICM probed by XRISM. These results provide a direct, spatially resolved view of gas dynamics within the inner few hundred parsecs, demonstrating the power of JWST/NIRSpec to probe SMBH feeding.

astro-ph.GA↗
arXiv2026

OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents

Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by look-ahead leakage, optimistic execution, and risk mandates that are described but not enforced. We present OpenPM, an auditable point-in-time evaluation framework for LLM portfolio-management agents. In OpenPM, an agent manages a \$1M long-only book over the S\&P 500 universe using market data at five-minute intervals. Every record visible to the agent must be available at the decision time. Natural-language risk mandates are converted into typed constraints and enforced on the executed portfolio. Each run produces audit artifacts, including a contamination certificate, a cost-sensitivity curve, and a constraint-adherence report. We also build a reference agent named the tiered allocator, where typed analysts score candidates, a constructor LLM proposes weights, and a deterministic critic guarantees feasibility. We isolate constructor behavior by capturing analyst evidence once and replaying it across constructor models. In our short-window case study, stronger constructors show modest and model-dependent gains over equal weighting on the same pool, but analyst quality matters more than constructor choice, and turnover is the main cost driver. All returns are upper bounds on a single frozen window without market impact, not validated alpha.

cs.CE↗
arXiv2026

NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception

Differentiable simulators have advanced policy learning and model-based control across robotic tasks. Yet actuator dynamics remain underexplored and can be a major source of sim-to-real error, particularly on low-cost platforms, where the linear current-to-joint-torque approximation $\tau = K_t I$ becomes unreliable because of friction, hysteresis, backlash, and thermal effects. Accurate actuator models can also support force perception and integrated force/position control. We present NeuralActuator, which jointly predicts (i) a torque surrogate for trajectory propagation on low-cost servo platforms, (ii) external forces with a contact-probability gate for sensorless force perception, and (iii) a motor-condition score for a supervised joint, distinguishing normal from mechanically restricted operation. A twin-arm teleoperation system records robot states and actuator telemetry alongside external-force labels, yielding the Neural Actuation Dataset (NAD). The torque-surrogate head is trained through differentiable simulation from pose trajectories without ground-truth joint-torque measurements. A Transformer captures temporal dependencies while enabling real-time inference. We validate NeuralActuator on a 5-DoF OpenManipulator-X, a 6-DoF SO-101 from LeRobot, and a 7-DoF Franka Emika Panda, spanning three actuator families and costs from approximately \$500 to more than \$30{,}000. The low-cost platforms support physically plausible dynamics and force evaluation, while the offline Franka experiment provides a payload-force-estimation benchmark. We also demonstrate motor-condition estimation and improved behavior-cloning performance using NeuralActuator as a pretrained module. We release the dataset, code, and hardware configurations on the project page: https://frank-zy-dou.github.io/projects/NeuralActuator/index.html.

cs.RO↗
arXiv2026

JWST reveals how black holes are fed: kiloparsec-scale multiphase filaments feed sub-kiloparsec circumnuclear disks

The Centaurus cluster is one of the most important archetypes of radio-mode AGN feedback, with its central galaxy, NGC 4696, launching powerful jets that inflate X-ray cavities and regulate cooling and star formation. NGC 4696 lies within a spectacular multiphase nebula of filaments extending over tens of kiloparsecs and spanning six decades in temperature, from hot (10^8 K) X-ray-emitting plasma to cold molecular gas. Owing to its proximity, Hubble Space Telescope H_alpha imaging reveals a striking S-shaped ionized-gas swirl within the black hole's sphere of influence - the first such structure identified in a cluster core. Here we present the first JWST observations of NGC 4696 with NIRSpec, probing the inner 618 pc * 618 pc at 10 pc resolution. These data reveal that the ionized swirl is a rotating, multiphase circumnuclear disk (CND) physically and kinematically connected to the larger-scale filamentary network. This provides the long-sought missing link between kiloparsec-scale cooling flows and black hole accretion on <100 pc scales. Strikingly, the observed morphology and kinematics are reproduced by tailored magnetohydrodynamic simulations, in which filamentary gas condenses from the hot atmosphere, loses angular momentum, and feeds a rotating CND that mediates accretion onto the black hole. A similar structure in NGC 1275, the Perseus cluster's central galaxy, together with our results on NGC 4696 - two prototypical radio-mode AGN feedback systems - points to a common mechanism: multiphase filaments transport gas from cluster scales down to the vicinity of the black hole via a CND, closing the AGN feedback loop and establishing a physically grounded framework for self-regulated galaxy evolution.

astro-ph.GA↗
arXiv2026

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only captions or textual traces, allowing answers to be inferred without preserving the fine-grained visual evidence. Meanwhile, harder cases that require reasoning over changing visual states are largely absent. Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures how retrieved evidence must be used (from single evidence to evolutionary synthesis). Under this framework, we construct a new benchmark across 8 life-scenario tasks, with ablation-driven validation gates for assessing answerability, shortcut resistance, visual necessity, and reasoning structure. By evaluating 13 memory methods across 4 VLM backbones, we show that current architectures still struggle to preserve fine-grained visual details and reason about state changes over time. Our findings show that long-term multimodal memory depends on evidence routing, temporal tracking, and detail extraction.

cs.CV↗
arXiv2026

WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer

A unified simulator that can model diverse physical phenomena without solver-specific redesign is a long-standing goal across simulation science. We present a learning-based particle simulator built on a single transformer architecture to model cloth, elastic solds, Newtonian and non-Newtonian fluids, granular materials, and molecular dynamics. Our model follows a prediction-correction design on a shared Lagrangian particle representation. An explicit predictor first advances particles under the known external forces, producing an intermediate state that captures externally driven motion but not inter-particle interactions. A learned corrector then predicts the residual position and velocity updates through three stages: a particle tokenizer that encodes local particle-particle, particle-boundary, and topology-guided interactions; a super-token encoder that hierarchically merges particle tokens into a compact set of super tokens via alternating self-attention and token merging; and a super-token decoder that lifts these super tokens back to particle resolution through cross-attention to predict per-particle position and velocity corrections. Progressive token merging reduces the attention cost at successive encoder layers by halving the token count at each level, and the decoder communicates through the compact super-token set rather than full particle-to-particle attention. Across the six dynamics categories, the same architecture generalizes to unseen materials, boundary configurations, initial conditions, and external forces. We further demonstrate downstream interactive control, inverse design, and learning from real-world manipulation data, reducing the need for per-phenomenon solver engineering.

cs.GR↗
arXiv2026

Hierarchical Transformer Preconditioning for Interactive Physics Simulation

Neural preconditioners for real-time physics simulation offer promising data-driven priors, but they often fail to capture long-range couplings efficiently because they inherit local message passing or sparse-operator access patterns. We introduce the Hierarchical Transformer Preconditioner, a neural preconditioner anchored to a weak-admissibility H-matrix partition. The partition provides a multiscale structural prior (dense diagonal leaves plus coarsening off-diagonal tiles) that enables full-graph approximate-inverse computation with O(N) scaling at fixed block sizes. The network models the inverse through low-rank far-field factors and uses highway connections (axial buffers plus a global summary token) to propagate context across transformer depth. At each PCG iteration, preconditioner application reduces to batched dense GEMMs with regular memory access. The key training contribution is a cosine-Hutchinson probe objective that learns the action of MA on convergence-critical spectral subspaces, optimizing angular alignment of MAz with z rather than forcing eigenvalue clusters to a prescribed location. This removes unnecessary spectral-placement constraints from SAI-style objectives and improves conditioning on irregular spectra. Because both inference and apply are dense, dependency-free tensor programs, the full solve loop is captured as a single CUDA Graph. On stiff multiphase Poisson systems (up to 100:1 density contrast, N = 1,024-16,384), the solver runs from ~143 to ~21 fps. At N = 8,192, it reaches 17.9 ms/frame, with 2.2x speedup over GPU Jacobi, ~28x over GPU IC/DILU (AMGX multicolor_dilu), and 2.7x over neural SPAI retrained per scale on the same benchmark.

cs.GR↗
arXiv2026

Neural Statistical Functions

Classical deep learning typically operates on individual cases. Despite its success, real-world usage often requires repeated inference to estimate statistical quantities for complex decision-making tasks involving uncertainty or extreme-value analysis, resulting in substantial latency. We introduce neural statistical functions, a new family of models learned from pre-trained single-sample predictors and scattered data samples, which can directly infer statistics over continuous operating condition ranges without explicit sampling. By introducing the notion of prefix statistics, we transform and unify diverse statistical functions (e.g., integrals, quantiles, and maxima) into an interval-conditional framework, in which a principled identity between the prefix statistics and the individual-case regression serves as the learning objective. Neural statistical functions achieve strong performance in estimating essential statistics of complex physical processes, including accumulated energy in dynamical systems, quantiles of aerodynamic responses, and maximum stress in crash processes, while achieving up to a 100$\times$ reduction in model evaluations.

cs.LG↗
arXiv2026

Trust or Abstain? A Self-Aware RAG Approach

Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are both unreliable. Existing approaches mainly coordinate which source to use, without explicitly asking whether each answer path is correct. We argue that faithful RAG requires LLM self-awareness, namely the ability to recognize the limits of its own knowledge and reasoning. To ground this problem, we construct a model-specific, ground-truth-aligned knowledge-conflict benchmark by evaluating LLM backbones on PK-only and CK-conditioned answer paths over approximately 69K query-context instances per backbone, drawn from five conflict-QA datasets. We then introduce SABER, a Self-Aware Belief Estimator for RAG that requires no LLM fine-tuning. SABER combines a self-prior with PK-side and CK-side conditional reasoning representations from multi-trace inference, then estimates reliability beliefs with two lightweight predictors to drive a 4-cell decision over trust PK, trust CK, trust either, or abstain. Across four LLM backbones, SABER improves end-to-end accuracy and conflict-specific faithfulness over ten inference-time and fine-tuning baselines, with the largest gains on conflict-heavy datasets. Under abstention, SABER's risk-coverage curve Pareto-dominates every prompt-based abstainer, providing a tunable balance between coverage and answer risk. Our code is available at https://github.com/xizhu1022/SABER.

cs.IR↗
arXiv2026

RigidFormer: Learning Rigid Dynamics using Transformers

Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-level message passing, which limits their applicability to mesh-free inputs such as point clouds and leads to high computational cost. Efficiently modeling high-fidelity rigid-body dynamics from mesh-free representations, therefore, remains challenging. We introduce RigidFormer, an object-centric Transformer-based model that learns mesh-free rigid-body dynamics with controllable integration step sizes. RigidFormer reasons at the object level and advances each object through compact anchors; Anchor-Vertex Pooling enriches these anchors with local vertex features, retaining contact-relevant geometry without dense vertex-level interaction. We propose Anchor-based RoPE to inject anchor geometry into attention while respecting the unordered nature of objects and anchors: object-token processing is permutation-equivariant, and the mean-pooled anchor descriptor is invariant to anchor reindexing while preserving shape extent. RigidFormer further enforces rigidity by projecting updates onto the rigid-body manifold using differentiable Kabsch alignment. On standard benchmarks, RigidFormer outperforms or matches mesh-based baselines using point inputs, runs faster, generalizes to unseen point resolutions and across datasets, and scales to 200+ objects; we also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.

cs.CV↗
arXiv2026

AEL: Evolving Agent Harness in Open-Ended Environments

LLM Agents Harnesses are hand-designed and stay fixed, so agents accumulate experience but never learn how to use it: which memories to retrieve, when retrieved evidence is misleading, and when the retrieval strategy itself should change. We introduce Agent Evolving Learning (AEL), a two-timescale framework that evolves the harness, recasting memory use as online policy selection. A fast Thompson Sampling bandit selects among memory-retrieval policies episode by episode, while slow LLM reflection follows a diagnose-before-prescribe principle: it first explains why performance degraded, then injects a targeted new retrieval policy as a bandit arm when the current pool plateaus. AEL outperforms ten self-improving and nonLLM baselines on a sequential portfolio benchmark, lifting Sharpe by 27% over the strongest memory-only variant with the lowest variance among all stochastic methods, and generalizes to a support-ticket routing stream, where it improves accuracy by 18% over reflectionfree Thompson Sampling and by 51% over the best prior baseline. Mechanism studies further show that the gains are causal: reflection helps precisely when regimes demand different retrieval behavior, and is provably no-harm/nogain when the best policy is stable. Code and data: https://github.com/WujiangXu/AEL.

cs.CL↗
arXiv2026

Raiven: LLM-Based Visualization Authoring via Domain-Specific Language Mediation

Visualization is central to scientific discovery, yet authoring tools remain split between information and scientific visualization, and expertise in one rarely transfers to the other. Large Language Model (LLM) based systems promise to bridge this gap through natural language, but current approaches generate code non-deterministically, with no guarantee of correctness and no protection against silent data fabrication. We present Raiven, a conversational system that mediates visualization authoring through a formally defined domain-specific language. RaivenDSL unifies scientific and information visualization in a single representation spanning 2D, 3D, and tabular data. The LLM produces a compact RaivenDSL specification under schema-guided constraints, and a deterministic compiler translates it to executable D3 or VTK.js code. Because the LLM operates only on dataset metadata, outputs are deterministic, specifications are verifiable before execution, and data fabrication is impossible by construction. In a 100-task benchmark, Raiven achieves 100% compilation, is up to six times faster and six times cheaper than state-of-the-art LLMs, while improving interaction quality, correctness, and data faithfulness. An expert user study shows that Raiven significantly reduces debugging effort and makes it easier to produce correct visualizations.

cs.HC↗
arXiv2026

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action heads incur high latency and compute, making real-time control expensive on commodity hardware. We present A1, a fully open-source and transparent VLA framework designed for low-cost, high-throughput inference without sacrificing manipulation success; Our approach leverages pretrained VLMs that provide implicit affordance priors for action generation. We release the full training stack (training code, data/data-processing pipeline, intermediate checkpoints, and evaluation scripts) to enable end-to-end reproducibility. Beyond optimizing the VLM alone, A1 targets the full inference pipeline by introducing a budget-aware adaptive inference scheme that jointly accelerates the backbone and the action head. Specifically, we monitor action consistency across intermediate VLM layers to trigger early termination, and propose Inter-Layer Truncated Flow Matching that warm-starts denoising across layers, enabling accurate actions with substantially fewer effective denoising iterations. Across simulation benchmarks (LIBERO, VLABench) and real robots (Franka, AgiBot), A1 achieves state-of-the-art success rates while significantly reducing inference cost (e.g., up to 72% lower per-episode latency for flow-matching inference and up to 76.6% backbone computation reduction with minor performance degradation). On RoboChallenge, A1 achieves an average success rate of 29.00%, outperforming baselines including pi0(28.33%), X-VLA (21.33%), and RDT-1B (15.00%).

cs.RO↗
arXiv2026

M-ABD: Scalable, Efficient, and Robust Multi-Affine-Body Dynamics

Simulating large-scale articulated assemblies poses a significant challenge due to the numerical stiffness and geometric complexity of jointed structures. Conventional rigid body solvers struggle with the high nonlinearity induced by rotation parameterization. This difficulty becomes more pronounced for multiple two-way-coupled bodies. This paper introduces a novel framework that leverages the linear kinematic mapping of Affine Body Dynamics (ABD). As ABD targets near-rigid objects, the constitutive variations of different materials become negligible, which justifies a co-rotational approach to isolate geometric nonlinearities of the system. This insight enables the use of constant system matrices that can be pre-factorized throughout the simulation, even with fully implicit integration schemes. To manage the high DOF counts of large-scale systems, we map primal body coordinates onto a compact dual space defined by minimal joint degrees of freedom. By solving the resulting KKT systems, our method ensures exact constraint enforcement and physically accurate motion propagation. We provide a suite of specialized solvers tailored for diverse joint topologies, including chains, trees, closed loops, and irregular networks. Experimental results show that our approach achieves interactive rates for systems with hundreds of thousands of bodies on a single CPU core, while maintaining excellent stability at large time steps.

cs.GR↗
arXiv2026

Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data

Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored. This paper presents a case study to investigate LLM-based individual simulation with a volunteer-contributed archive of private messaging history spanning over ten years. Based on the messaging data, we propose the "Individual Turing Test" to evaluate whether acquaintances of the volunteer can correctly identify which response in a multi-candidate pool most plausibly comes from the volunteer. We investigate prevalent LLM-based individual simulation approaches including: fine-tuning, retrieval-augmented generation (RAG), memory-based approach, and hybrid methods that integrate fine-tuning and RAG or memory. Empirical results show that current LLM-based simulation methods do not pass the Individual Turing Test, but they perform substantially better when the same test is conducted on strangers to the target individual. Additionally, while fine-tuning improves the simulation in daily chats representing the language style of the individual, retrieval-augmented and memory-based approaches demonstrate stronger performance on questions involving personal opinions and preferences. These findings reveal a fundamental trade-off between parametric and non-parametric approaches to individual simulation with LLMs when given a longitudinal context.

cs.CL↗
arXiv2026

GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training

Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural alternative, yet faces a fundamental gap: supervision on static geometry alone ignores dynamics and can lead to negative transfer on physics tasks. We present GeoPT, a unified pre-trained model for general physics simulation based on lifted geometric pre-training. The core idea is to augment geometry with synthetic dynamics, enabling dynamics-aware self-supervision without physics labels. Pre-trained on over one million samples, GeoPT consistently improves industrial-fidelity benchmarks spanning fluid mechanics for cars, aircraft, and ships, and solid mechanics in crash simulation, reducing labeled data requirements by 20-60% and accelerating convergence by 2$\times$. These results show that lifting with synthetic dynamics bridges the geometry-physics gap, unlocking a scalable path for neural simulation and potentially beyond. Code is available at https://github.com/Physics-Scaling/GeoPT.

cs.LG↗