Search arXiv⌕ Search

arXiv subjects

Zhi Wang

Publications and source records attributed to Zhi Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Grounding Large Language Models as Generalizable Policies in Network Control

Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital infrastructure. Yet network control remains dominated by specialized policies built from handcrafted rules or deep learning models, which struggle to generalize under real-world dynamics. Large language models (LLMs) offer a promising alternative because of their broad pretrained knowledge and emergent generalization abilities, but their practical adoption in network control is hindered by non-textual observations, constrained action spaces, complex optimization knowledge, and strict real-time requirements. Therefore, we introduce Trailblazer, a systematic framework that combines domain alignment to adapt LLMs for network control with adaptive policy collaboration to reduce inference overhead. Simulations across two heterogeneous network control tasks, adaptive bitrate streaming and cluster job scheduling, show that Trailblazer improves performance over conventional policies by 6.5%-36.6% and 3.5%-41.3%, respectively. Moreover, in a large-scale online A/B test of congestion control on Douyin, Trailblazer outperforms a highly optimized industrial policy, corresponding to a projected reduction of approximately 3,145 hours of platform-wide video stall time per day. Further analysis reveals that effective LLM-based control can be achieved by properly aligning compact LLMs and only invoking them for complex conditions, rather than model scaling or extensive invocation. Together, our results establish an LLM-driven paradigm for designing generalizable network policies and offer practical insights into grounding foundation models for real-world network control.

cs.LG↗
arXiv2026

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision. We argue this assumption is flawed: a strong teacher often reaches the correct answer without needing its tool calls, and imitating such trajectories teaches a student that tool calls accompany correct answers, not that tool observations ground them. We present OpenVisTool, an open framework for constructing instructive visual tool-use trajectories that provide effective supervision for tool learning. The key insight is that a trajectory should be retained only if its answer is correct (outcome validity) and its tool observations causally contribute to that answer (causal utility). The framework operates in three stages: difficulty screening to select queries that are not reliably answerable without tools, domain-specific trajectory synthesis to elicit coherent tool-use trajectories, and supervision verification to jointly test both conditions. Rather than encouraging models to imitate tool calls, the resulting supervision teaches when and how visual evidence should be acquired. Using this framework, we construct OpenVisTool-42K, a dataset spanning five visual reasoning domains, together with OpenVisTool-Bench, a benchmark covering the same domains. Across four backbones (4B-27B), fine-tuning on OpenVisTool-42K consistently improves visual tool-use performance and yields gains on two out-of-distribution benchmarks; the larger models approach leading closed-source systems. The evidence suggests that effective visual tool use is learned from causally grounded supervision rather than tool-calling patterns.

cs.CL↗
arXiv2026

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents

Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts. However, even strong code agents repeatedly fail on a substantial fraction of such tasks, and standard RFT simply discards these failures. The discarded samples are precisely the hardest and most informative ones, drawn from verifiable instances that are costly to curate. Stronger base models may reduce the number of failures, but the remaining hard cases still define the frontier for further improvement. We propose FailForge, an agentic framework that converts failed rollouts into training signal. For each failed instance, an agent diagnoses the failure from error feedback and execution traces, distills the diagnosis into a concise and actionable skill, and injects the skill into the agent context for a guided second attempt. Trajectories that succeed under skill guidance are folded back into the RFT corpus. Crucially, the skill is removed at training time, so the model internalizes the recovered behavior rather than relying on external hints at inference. FailForge recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline, with gains concentrated on the hardest problems.

cs.AI↗
arXiv2026

Berry curvature effects of chiral superconducting rhombohedral graphene

We study the Berry curvature effects of the Bogoliubov quasiparticles in chiral superconducting rhombohedral graphene. Using a two-band Bogoliubov-de Gennes Hamiltonian to describe the superconducting quasiparticles, we calculate the momentum-space Berry curvature, orbital magnetic moment, and anomalous thermal Hall, spin Nernst, and orbital Nernst transport of chiral $p$-wave superconducting states. We investigate the impact of normal-state band warping in rhombohedral graphene, which can generate Bogoliubov Fermi surfaces for quasiparticle excitations. We find that Bogoliubov Fermi surfaces qualitatively modify the anomalous transport responses, inducing a deviation of the thermal Hall conductivity from the quantized value and strongly enhancing the spin and orbital Nernst responses.

cond-mat.supr-con↗
arXiv2026

Semiclassical theory for the orbital magnetic moment of superconducting quasiparticles

We study the orbital magnetic moment of Bogoliubov quasiparticles in superconductors with the semiclassical approach. We derive the orbital magnetic moment of a quasiparticle wavepacket by considering the energy correction of the wavepacket to the linear order of the magnetic field. The semiclassical result is further verified by a linear response calculation with a full quantum mechanical method. From the analytical expression we find that nontrivial structure in the superconducting pairing gap alone is unable to produce quasiparticle orbital magnetic moment, which is in sharp contrast to the behavior of quasiparticle Berry curvatures. We apply the formula to study a tight-binding model with chiral $d$-wave superconducting gap, and show the influence of orbital magnetic moment on the energy spectrum and local density of states. We also calculate the orbital Nernst effect driven by the interplay between the orbital magnetic moment and the Berry curvature of Bogoliubov quasiparticles.

cond-mat.supr-con↗
arXiv2026

ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation

Humans perform long-horizon manipulation by retaining knowledge of what earlier actions have established while continuously adapting the motion underway. By contrast, action-chunked vision-language-action (VLA) policies repeatedly replan from the current input at each query. Existing methods preserve either long-term task evidence through memory or short-term motion through action reuse and ensembling, leaving the cross-query handoff incomplete. We introduce ChainVLA, a 1.2B-parameter VLA policy that chains successive queries through a joint and revisable execution state. Progress Context combines a recurrent Working State with sparse event memory to carry observation-derived task progress, while Motion Tail feeds the preceding prediction's unexecuted continuation into state construction and action generation. Together, the two components condition a decoder that regenerates each action horizon under the latest observation, allowing the carried state to guide the next prediction without fixing it. ChainVLA reaches 62.8% average success on RMBench and 98.8% across four LIBERO suites, while removing Motion Tail or Progress Context reduces RMBench success to 11.2% and 3.0%, respectively. These asymmetric ablations are consistent with motion continuity helping preserve the observation stream from which task progress is inferred.

cs.RO↗
arXiv2026

Occupation-Driven emission asynchronous as a Fundamental Constraint on Solid-State Attosecond Pulses

A newly analytic occupation-resolved theory capturing the temporal structure of attosecond pulses (APs) is derived. We validate it with real-time time-dependent density functional theory and show remarkable temporal confinement of APs with laser intensity in solid state. Using a simplified field-driven electron excitation together with a generalized pre-acceleration picture, the interband emission timing demonstrate intrinsically temporal mismatched with field-synchronous intraband radiation, leading to a nonmonotonic dependence of attosecond pulse width on laser intensity. Our findings not only shed light on the microscopic mechanisms behind solid-state high harmonic generation (HHG), but also establish the fundamental time-domain constraint on solid-state APs independent of material damage thresholds.

physics.optics↗
arXiv2026

Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition

Accurate 3D part decomposition requires separating shapes into structurally meaningful components with precise boundaries while preserving articulation seams and thin attachments. Existing approaches often suffer from a structural-scale mismatch: geometric evidence for separation is most reliable at the meso scale, yet many pipelines operate either too globally to respect joints or too locally to remain robust to noise. We propose Hi-TOPS, a Hierarchical Topology-aware Scoring Prior that aggregates complementary intrinsic cues into a multi-resolution Flow-Freeze field. Flow regions provide expandable support for primitive coverage, while Freeze regions restrict growth near articulations and thin structures. A TSDF-guided body-surface superquadric fitter then captures dominant cores and residual surface structures, followed by SQ-to-mesh assignment for connected, boundary-aligned parts. Across diverse benchmarks, Hi-TOPS delivers stable, editable decompositions without semantic supervision or 2D foundation priors.

cs.GR↗
arXiv2026

DuetHOI: Language-Guided Bimanual Hand--Object Motion Generation with Articulation Planning and Contact Refinement

Bimanual articulated-object interaction generation requires a model to capture the evolution of object articulation, coordination between the two hands, and fine-grained hand--object contact. Existing methods typically encode object and hand motion as a unified high-dimensional sequence, making it difficult to explicitly accommodate the different scales of manipulation progress, relative bimanual motion, and local hand pose. We propose \textbf{DuetHOI}, a structured framework for bimanual articulated-object interaction generation. DuetHOI first uses ContactVAE to predict contact intent on the object surface from language and object geometry. Conditioned on this spatial intent, ArtPlanner provides a trajectory-level articulation reference, and DualFormer generates the global interaction using object states, object-centered hand positions, and compact hand-pose tokens learned by ManiVAE. After global generation, ProxiRefine fixes the object trajectory and residually corrects the two hands using current hand--object proximity, improving local surface alignment. Experiments across articulated and rigid objects and single- and bimanual settings show that DuetHOI outperforms three adapted baselines on most contact and hand--object consistency metrics, with particularly strong results in bimanual articulated interaction generation.

cs.RO↗
arXiv2026

SAIL: Perceptual Quality-Aware Rate Control for Cloud Gaming

Cloud gaming streams cloud-rendered frames under strict motion-to-photon latency, yet its at-scale viability is increasingly constrained by bandwidth cost: in our study of the T cloud gaming platform, bandwidth accounts for 30-60% of total operating expense. This high bandwidth consumption stems from a fidelity-first objective of making the stream perceptually indistinguishable from local gameplay. It drives production systems toward best-effort bitrate allocation that pushes the encoder to the highest rate allowed by congestion control. However, the bitrate-perception relationship saturates: beyond a frame-dependent perceptually lossless threshold, additional bits yield negligible perceptual improvement, creating systematic redundant quality that wastes bandwidth. We present SAIL, a production quality-aware rate control system with the goal of achieving perceptually lossless quality while avoiding unnecessary bandwidth waste. SAIL adopts a post-encoding architecture to enable millisecond-scale feedback at near-zero overhead. It comprises three key designs: (i) an encoder-driven quality assessment model that leverages zero-cost encoder outputs for real-time quality estimation; (ii) a hybrid rate control mechanism that balances steady-state adaptation with dynamic spike absorption; and (iii) a network-aware strategy that coordinates with congestion control to prevent capacity underestimation. SAIL has been fully deployed on the T cloud gaming platform and reduces bandwidth consumption by 44.27% and end-to-end latency by 8.37% without degrading perceived quality, serving tens of millions of users and accumulating billions of hours of total gameplay.

cs.NI↗
arXiv2026

Learning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance

Most neural partial differential equation (PDE) surrogates learn how fields evolve after a grid has already been chosen. However, before any operator is applied, the grid has already determined how modeling capacity is allocated across space, resolution, and spectral bandwidth. We argue that this hidden design choice should itself be learnable, leading to a question different from standard operator learning: can a surrogate learn where resolution should exist before predicting field evolution? We formulate adaptive discretization as a physics-constrained conditional generation problem over valid mesh displacements. The success of diffusion models in PDE field prediction suggests their potential for learning adaptive discretizations under similar structured constraints. This leads to a two-stage diffusion framework: Stage 1 learns an r-adaptive displacement mesh conditioned on the observed dynamics, while Stage 2 predicts the solution evolution from the mesh-informed representation. The mesh generator is regularized by physics-aware proxy channels, geometric validity constraints, and local spectral concentration so that adaptation remains physically interpretable and numerically legal. Across five PDE regimes, the results show that diffusion-based learned discretization is competitive with adaptive-mesh and reduced-order baselines, with particularly strong gains in regimes where fixed or handcrafted allocation is insufficient. The main conclusion is not that there exists a universal optimal mesh rule, but that discretization should be learned in a regime-dependent manner: different spatial and spectral structures favor different allocation behaviors. This reframes adaptive meshing for neural PDE solvers from a solver-specific heuristic into a generative representation-learning problem.

cs.LG↗
arXiv2026

RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

Enabling reliable long-horizon robotic manipulation is a crucial step toward open-world embodied intelligence. However, VLM-based planners treat each step as an isolated observation-to-action mapping, forcing them to reinfer scene geometry from raw pixels at every decision point while remaining unaware of how prior actions have reshaped the environment. Despite strong short-horizon performance, these systems lack the spatio-temporal reasoning required for persistent geometric anchoring and memory of action-triggered state transitions. Without persistent state tracking, perceptual errors accumulate across the execution horizon, temporarily occluded objects are catastrophically forgotten, and these compounding failures lead to precondition violations that cascade through subsequent steps. In contrast, humans maintain a persistent mental model that continuously tracks spatial relations and action consequences across interactions rather than reconstructing them at each instant. Inspired by this human capacity for causal spatio-temporal reasoning with persistent memory, we propose RoboStream, a training-free framework that achieves geometric anchoring through Spatio-Temporal Fusion Tokens (STF-Tokens), which bind visual evidence to 3D geometric attributes for persistent object grounding, and maintains causal continuity via a Causal Spatio-Temporal Graph (CSTG) that records action-triggered state transitions across steps. This design enables the planner to trace causal chains and preserve object permanence under occlusion without additional training or fine-tuning. RoboStream achieves 90.5% on long-horizon RLBench and 44.4% on challenging real-world block-building tasks, where both SoFar and VoxPoser score 11.1%, demonstrating that spatio-temporal reasoning and causal memory are critical missing components for reliable long-horizon manipulation.

cs.RO↗
arXiv2026

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Existing approaches apply RL exclusively to text steps, relegating image generation to supervised surrogates, preventing policy gradients from propagating through the full interleaved trajectory across heterogeneous modalities. This leaves the potential of RL for UMMs largely untapped. In the paper, we introduce \textbf{BRAID} (\textbf{B}ridging inte\textbf{R}le\textbf{A}ved mult\textbf{I}-modal reasoning as a unified \textbf{D}ecision process), a simple framework that casts multi-turn text-image-text reasoning as a unified Markov decision process (MDP), enabling joint optimization of textual and visual generation via a single, principled RL objective. BRAID computes a shared trajectory-level advantage and propagates it coherently into both text tokens and image denoising paths, each optimized through its modality-native policy gradient mechanism. To further address long-horizon credit assignment, BRAID employs a vision-language model (VLM) judge that scores each intermediate image on its reasoning utility, supplying dense turn-level feedback to sharpen learning at critical visual branches. Experiments on spatial reasoning and visual perception benchmarks show that BRAID consistently outperforms various baselines, confirming that a unified MDP formulation with vision-thinking guidance is essential for effective multi-modal reasoning.

cs.AI↗
arXiv2026

Atomic Task Graph: A Unified Framework for Agentic Planning and Execution

LLM-based agents have shown strong potential for solving complex multi-step tasks, yet existing performance improvements often rely on either scaling to larger backbone models or task-specific fine-tuning. The former incurs substantial computational costs, while the latter typically generalizes poorly across different tasks. Although prompt-based control is training-free and broadly applicable, existing methods still leave input-output dependencies between subtasks implicit in textual trajectories, making verified intermediate results difficult to reuse. To address these limitations, we propose Atomic Task Graph (ATG), a unified control framework for planning and execution. Specifically, ATG maintains an explicit graph to expose dependencies and support reuse. During planning, it recursively decomposes a high-level task into subtasks, forming a sequence of directed acyclic graphs (DAGs) whose evolution can be traced. During execution, the dependencies exposed by ATG allow independent branches to be executed in parallel, thereby improving execution efficiency. When failures are detected, ATG leverages the graph evolution history to localize the error source and repair only the affected region, preserving validated regions unchanged. Experiments show that ATG consistently outperforms strong baselines in success rate and execution efficiency across three interactive benchmarks using only 7B-8B backbones.

cs.AI↗
arXiv2026

Surface code logical operations on a superconducting quantum processor

Fault-tolerant quantum computation requires logical operations that manipulate encoded information while preserving quantum error-correction protection. In planar surface-code architectures, code deformation and lattice surgery provide a local, measurement-based route to such operations. Here we experimentally realize key elements of patch-based surface-code logical processing on a 107-qubit superconducting quantum processor. We first implement a reusable primitive layer comprising merge and split, patch expansion and shrinkage, and deformations mediated by domain walls and twist defects. We then compose these primitives to realize logical state routing, the logical controlled-NOT gate, and the single-qubit Hadamard and phase gates, which together form a Clifford-generating set. All operations are implemented on distance-three rotated surface-code patches with multi-round syndrome extraction and neural-network decoding, without post-selection. Our results advance superconducting surface-code experiments from protected logical memory to active, patch-based fault-tolerant logical operations.

quant-ph↗
arXiv2026

ForceBand: Learning Forceful Manipulation with sEMG

Human demonstrations are a scalable data source for learning robot manipulation policies. However, common sources of human demonstration data, such as motion-capture trajectories and internet videos, capture mostly motion and appearance while missing the contact forces that are critical for force-sensitive manipulation. In this paper, we introduce ForceBand, a low-cost wrist-worn sEMG system that turns human muscle activity into force-enriched demonstrations. We first collect a 10-hour multimodal dataset containing egocentric video, sEMG, IMU, and fingertip force measurements across diverse actions and objects. Using this dataset, we pre-train an EMG2Force model that predicts per-finger forces from sEMG and IMU signals. After a short user-specific calibration, users can collect target-task demonstrations using only ForceBand and video; EMG2Force then labels these demonstrations with per-finger force traces, producing force-augmented demonstrations for robot policy learning. Experiments show that ForceBand recovers fine-grained fingertip interactions with over 50% lower force prediction error than vision-based baselines and achieves an 87% success rate on pick, squeeze, and place tasks that require object-specific force control across objects with diverse shapes, sizes, and weights. Project website: https://forceband-emg.github.io

cs.RO↗
arXiv2026

Social Structure Matters in 3D Human-Human Interaction Generation

Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requires modeling the underlying \textbf{social structure} that governs phase progression, actor roles, and inter-actor coordination. In this paper, we formulate HHI generation as a social structure modeling and grounding problem: the model must first infer how an interaction unfolds and how the two actors coordinate their roles, and then realize this structure as continuous, physically plausible, and partner-aware 3D motion. To study how such structure should be modeled, we first examine the capability boundary of large language models (LLMs) for HHI generation. Our analysis shows that LLMs can \textit{think} by recovering phase decompositions and partner-aware roles, but cannot directly \textit{move}, as they fail to generate dynamic, physically plausible, and interaction-aware motion. This motivates our planner-executor paradigm, \textbf{Think with LLM, Move with Motion Skill}. The LLM planner converts implicit interaction semantics into motion-aligned social supervision by decomposing interactions into phases, assigning partner-aware actor roles, and aligning them with motion sequence. The motion executor then grounds the planned social structure into coordinated two-person motion by adapting a pretrained solo motion model with LoRA, previous-phase self-conditioning, and ego-relative partner conditioning. Together, our Solo-to-Social framework bridges social organization and motion realization, producing 3D HHI with improved phase consistency, role alignment, and partner-aware coordination.

cs.CV↗
arXiv2026

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In this paper, we propose MA-RAG (Multi-Round Agentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic conflict among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the self-consistency principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a boosting mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical consensus. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering substantial +6.8 points on average accuracy over the backbone model. Our code is available at https://github.com/NJU-RL/MA-RAG.

cs.CL↗