arXiv subjects

Jia Luo

Publications and source records attributed to Jia Luo.

11 recordsLinked to original sources

arXiv2026

SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering

AI agents increasingly rely on large skill libraries, but selecting, combining, and maintaining skills remains difficult. We propose SKIMIX, a multi-agent framework in which agents with different skill portfolios collaborate through iterative refinement. SKIMIX combines embedding-based skill retrieval, submodular anti-dilution routing, and adaptive skill evolution. Across six reasoning benchmarks, multi-agent collaboration substantially improves open-ended mathematical reasoning but offers limited or negative gains on multiple-choice tasks. Agent-count scaling is non-monotonic, and most improvements arise during the first refinement round. These results show that task characteristics determine whether skill-level ensembles help and provide practical guidance for scalable agent design.

cs.AI↗

arXiv2026

From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence

The key bottleneck in embodied AI is not model architecture but data. Although billions of human manipulation videos exist online, robots cannot directly learn from them due to the embodiment gap between human morphology and robot hardware. We introduce Pegasus, a low-resource framework that bridges this gap by translating human demonstrations into robot-learnable data through structured knowledge transfer. Instead of relying on raw video prompts, Pegasus constructs a graph-based intermediate representation: a Task Graph extracted from human videos is transformed through Affordance and Constraint Graphs into a Robot Planning Graph for robot-conditioned video generation. A hierarchical affordance latent space models the relationship between object states, affordances, and tasks, enabling generalization beyond object identities. A closed-loop physics verifier further filters invalid generations using kinematic feasibility, collision constraints, and joint limits. We evaluate Pegasus across a range of egocentric manipulation benchmarks, including GTEA Gaze+ and EPIC-KITCHENS-100, and diverse robot embodiments, assessing Task Correctness, Executability, State Consistency, and Learnability. Results demonstrate reliable cross-embodiment translation and show that robot data generation can be reframed from a hardware collection problem into a scalable, low-resource knowledge transfer problem.

cs.AI↗

arXiv2026

ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience

AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints. We introduce REFLECTICHAIN, bridging this gap through a Generative Supply Chain World Model (SC-WM) - encoding heterogeneous supply networks into a 6-dim graph-latent space with physical conservation - and Double-Loop Learning that separates epistemic uncertainty (KL-trust-region-bounded policy adaptation) from aleatoric uncertainty (stochastic latent rollouts). On Semi-Sim, a 10-node semiconductor benchmark with SIR risk propagation, 6 perturbation types, and 10 policy constraint templates, REFLECTICHAIN improves Rationale Consistency Score by 33.0% (p < 0.0001, d = 2.78), maintains 82.3% operability under adversarial shocks, and exhibits anti-fragile behavior (+40.2% gain under moderate pressure). We identify three operational epistemic mechanisms - uncertainty separation, knowledge-boundary detection, and empirical Bayesian policy updating - and discuss five limitation categories.

cs.AI↗

arXiv2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

cs.CL↗

arXiv2026

From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience

Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.

cs.AI↗

arXiv2025

Phase-based stimulated emission depletion (pSTED) magnetic particle imaging

Magnetic particle imaging (MPI) is an in vivo method to detect magnetic nanoparticles for cell tracking, vascular imaging, and molecular target imaging without ionizing radiation. Current magnetic particle imaging is accomplished by forming an field-free line (FFL) through a gradient selection field. By translating and rotating FFL under excitation and drive fields, the harmonic complex signal of a point source forms a Lorentzian-shape point spread function on the plane perpendicular to FFL. The Lorentzian PSF has a finite size and limited resolution due to the non-sharp Langevin function and weak selection field. This study proposes a donut-shaped focal spot by borrowing the stimulated emission depletion (STED) fluorescence microscopy principle. The influence of the gradient selection field on the relaxation time of magnetic particles determines the nonlinear phase shift of the harmonic complex signals, resulting in the formation of a donut-shaped focal spot. By subtracting the donut-shaped focal spot from the Lorentzian focal spot, the STED focal spot size was reduced by up to 4 times beyond the Langevin magnetization resolution barrier. In human brain FFL-based MPI scanner, the donut-shaped focal spot can be used to reconstruct images with super-resolution and super-sensitivity through the deconvoution of the STED focal spot and filtered backprojection algorithm.

physics.med-ph↗

arXiv2025

Extended Hybridization Expansion Solver for Impurity Models with Retarded Interactions

We extend the continuous-time hybridization expansion solver to a general form, where the hybridization function and retarded interaction are treated on equal footing. Correlation functions can now be directly obtained via functional derivatives with respect to the bosonic propagators, similar to the measurement of Green's functions. We devise a combinatorial scheme of measuring the correlation function, whose efficiency partially emulates that of the Green's function measurement. The algorithm and numerical methods are validated through application to an impurity model involving both electron-phonon coupling and exchange interactions, a case where the previous hybridization expansion algorithm is not applicable. Our improvement of the hybridization expansion solver promotes its applicability in studies of electron-phonon coupling, the extended dynamical mean field theory, and the dual boson method.

cond-mat.str-el↗

arXiv2023

A Comparative Analysis of the COVID-19 Infodemic in English and Chinese: Insights from Social Media Textual Data

The COVID-19 infodemic, characterized by the rapid spread of misinformation and unverified claims related to the pandemic, presents a significant challenge. This paper presents a comparative analysis of the COVID-19 infodemic in the English and Chinese languages, utilizing textual data extracted from social media platforms. To ensure a balanced representation, two infodemic datasets were created by augmenting previously collected social media textual data. Through word frequency analysis, the thirty-five most frequently occurring infodemic words are identified, shedding light on prevalent discussions surrounding the infodemic. Moreover, topic clustering analysis uncovers thematic structures and provides a deeper understanding of primary topics within each language context. Additionally, sentiment analysis enables comprehension of the emotional tone associated with COVID-19 information on social media platforms in English and Chinese. This research contributes to a better understanding of the COVID-19 infodemic phenomenon and can guide the development of strategies to combat misinformation during public health crises across different languages.

cs.SI↗

arXiv2019

A Survey on Parallel Genetic Algorithms for Shop Scheduling Problems

There have been extensive works dealing with genetic algorithms (GAs) for seeking optimal solutions of shop scheduling problems. Due to the NP hardness, the time cost is always heavy. With the development of high performance computing (HPC) in last decades, the interest has been focused on parallel GAs for shop scheduling problems. In this paper, we present the state of the art with respect to the recent works on solving shop scheduling problems using parallel GAs. It showcases the most representative publications in this field by the categorization of parallel GAs and analyzes their designs based on the frameworks.

cs.DC↗

arXiv2019

A Dual Heterogeneous Island Genetic Algorithm for Solving Large Size Flexible Flow Shop Scheduling Problems on Hybrid multi-core CPU and GPU Platforms

The flexible flow shop scheduling problem is an NP-hard problem and it requires significant resolution time to find optimal or even adequate solutions when dealing with large size instances. Thus, this paper proposes a dual island genetic algorithm consisting of a parallel cellular model and a parallel pseudo model. This is a two-level parallelization highly consistent with the underlying architecture and is well suited for parallelizing inside or between GPUs and a multi-core CPU. At the higher level, the efficiency of island GAs is improved by exploring new regions within the search space utilizing different methods. In the meantime, the cellular model keeps the population diversity by decentralization and the pseudo model enhances the search ability by the complementary parent strategy at the lower level. To encourage the information sharing between islands, a penetration inspired migration policy is designed which sets the topology, the rate, the interval and the strategy adaptively. Finally, the proposed method is tested on some large size flexible flow shop scheduling instances in comparison with other parallel algorithms. The computational results show that it cannot only obtain competitive results but also reduces execution time.

cs.DC↗

arXiv2019

GPU based parallel genetic algorithm for solving an energy efficient dynamic flexible flow shop scheduling problem

Due to new government legislation, customers' environmental concerns and continuously rising cost of energy, energy efficiency is becoming an essential parameter of industrial manufacturing processes in recent years. Most efforts considering energy issues in scheduling problems have focused on static scheduling. But in fact, scheduling problems are dynamic in the real world with uncertain new arrival jobs after the execution time. This paper proposes a dynamic energy efficient flexible flow shop scheduling model using peak power value with the consideration of new arrival jobs. As the problem is strongly NP-hard, a priority based hybrid parallel Genetic Algorithm with a predictive reactive complete rescheduling approach is developed. In order to achieve a speedup to meet the short response in the dynamic environment, the proposed method is designed to be highly consistent with NVIDIA CUDA software model. Finally, numerical experiments are conducted and show that our approach can not only achieve better performance than the traditional static approach, but also gain competitive results by reducing the time requirements dramatically.

cs.DC↗