arXiv subjects

Beibei Xu

Publications and source records attributed to Beibei Xu.

4 recordsLinked to original sources

arXiv2026

Dittany: Contribution-Guided Repair Framework for MAS Applications

LLM-based multi-agent system (MAS) applications can produce useful intermediate results while leaving task requirements unsatisfied. Repairing such executions requires identifying the work still needed and the completed results that can support it. We present \tool, a contribution-guided runtime repair framework for MAS applications. \tool derives expected contributions and acceptance conditions from task requirements and method specifications, and connects their dependencies in a contribution graph. Runtime checks locate unmet conditions and establish which results remain usable. These results guide action-level correction when available inputs suffice, or graph-level recovery when prerequisites or unfinished work need revision. Both repair scopes retain validated contributions and check repaired outputs before subsequent work uses them. We evaluate \tool on 30 applications across six MAS frameworks and 9,000 tasks. It detects runtime failures with 88.28\% precision and 79.18\% recall, and achieves 84.76\% task accuracy, improving over Native execution by 26.74 percentage points and the strongest of four recovery baselines by 21.28 points. Estimated deployment token consumption is 17.92\% above Native, but 24.19\% below Reflexion and 13.05\% below Iterative Rollback. Ablation results show that combining the two repair scopes achieves higher accuracy and lower token consumption than graph-level repair alone.

cs.SE↗

arXiv2026

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.

cs.AI↗

arXiv2025

Exploration of Multi-Element Collaborative Research and Application for Modern Power System Based on Generative Large Models

The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.

eess.SY↗

arXiv2012

Photoluminescence from Bi5(GaCl4)3 molecular crystal

Bi5(GaCl4)3 sample has been synthesized through the oxidation of Bi metal by gallium chloride (GaCl3) salt. Powder X-ray diffraction as well as micro-Raman scattering results revealed that, in addition to crystalline Bi5(GaCl4)3 in the product, amorphous phase containing [GaCl4]- and [Ga2Cl7]- units also exist. The thorough comparison of steady-state and time-resolved photoluminescent behaviors between Bi5(GaCl4)3 product and Bi5(AlCl4)3 crystal leads us to conclude that Bi53+ is the dominant emitter in the product, which gives rise to the ultrabroad emission ranging from 1 to 2.7 micrometer. Detailed quantum chemistry calculation helps us assign the observed excitations to some electronic transitions of Bi53+ polycation, especially at shorter wavelengths. It is believed that our work shown here not only is helpful to solve the confusions on the luminescent origin of bismuth in other material systems, but also serves to develop novel broadband tunable laser materials.

cond-mat.mtrl-sci↗