Searcharxiv⌕ Search

arXiv subjects

Cao

Publications and source records attributed to Cao.

6 recordsLinked to original sources

Time-Consistent Evaluation of Hierarchical Code Graphs for SWE Agents

Evaluating repository-aware software engineering (SWE) agents requires strict separation between pre-existing repository knowledge and future code evolution, yet standard benchmarks frequently suffer from temporal contamination and prompt-level solution leakage. Building on the time-consistent benchmark protocol of Sun (2026), we enforce strict zero-leakage isolation across DragonFly in C++ and React in JavaScript/TypeScript, locking repository snapshots and knowledge graphs at historical cutoff commits $T_0$ and evaluating 100 post-$T_0$ pull requests across four prompt granularities: Minimal, Concise, Contextual, and Guided. Under this zero-leakage protocol, we conduct a matched evaluation of three context-augmentation regimes: (1) an unaugmented Baseline, (2) a flat syntax-level Tree-sitter AST graph, and (3) ServiceExplorer, a deterministic two-level hierarchical dependency graph capturing Level-1 system/package containers and Level-2 architectural modules. Across 7,200 paired evaluations spanning six foundation models across the MAI-Code Flash, Claude, and GPT-Sol families, ServiceExplorer consistently outperforms both Baseline and Tree-sitter AST across every model, repository, and prompt granularity ($+15.6\%$ to $+86.2\%$ relative $F_1$ lift, $p < 10^{-4}$), while tripling exact full-PR localization on DragonFly. Crucially, equipping an efficiency-tier or prior-generation model with ServiceExplorer consistently surpasses the unaugmented Baseline $F_1$ of the next-generation model across all evaluated families.

cs.SE↗

The Defense Rests: A Courtroom-Inspired Multi-Agent LLM Framework for Automated Safety Case Generation

Safety cases are widely used to demonstrate that mission-critical systems, such as autonomous vehicles and unmanned aerial systems, can operate safely after deployment. However, manually constructing safety cases is complex, time-consuming, and labor-intensive, which calls for the proposal of automated approaches to support their creation. Inspired by the legal nature of safety case construction, we formalize the safety case creation problem through a courtroom analogy, where stakeholders collaboratively propose, examine, criticize, review, improve and validate safety claims and their supporting evidence. In this analogy, the safety analyst acts as a prosecutor by identifying hazards and safety concerns, while the assurance case developer serves as a defense attorney by constructing and substantiating safety arguments. An orchestrator acts as a judge by coordinating stakeholder interactions, and a review board serves as a jury by assessing argument completeness and persuasiveness. Based on this formalization, we propose eTrustWare, a Large Language Model (LLM)-based multi-agent framework for automated safety case generation and review. Our experiments on several safety cases of ML-enabled autonomous driving systems demonstrate the feasibility of coordinated LLM-based agents for generating safety cases.

cs.SE↗

Artificial Intelligence for Power-Converter-Rich Electrical Systems: A Review

Power-converter-rich electrical systems, formed by renewable generation, electrified transportation, and inverter-based resources, exhibit strongly nonlinear dynamics, multi-physics design tradeoffs, fast control requirements, and growing reliability and cybersecurity constraints. These characteristics strain workflows that rely only on physics-based modeling, sequential optimization, and rule-based operation. This paper reviews artificial intelligence (AI) for power-converter-rich electrical systems through a life-cycle and deployment-readiness perspective. The literature is organized across converter design, real-time control, system-level operation, and compliance-oriented governance. For design, we examine surrogate modeling, topology and parameter synthesis, EMI/EMC-aware optimization, reliability-oriented design, and knowledge-assisted workflows. For control, we compare supervised learning, reinforcement learning, learning-augmented predictive control, and safety-constrained learning according to their role in closed-loop implementation. For operations, we focus on microgrid coordination, forecasting, distribution-system observability, privacy-preserving coordination, and cyber-resilient operation where converter-interfaced resources shape the operating problem. Across these stages, the review emphasizes deployment-critical gaps, including stability certification, constraint satisfaction, interpretability, extrapolation, data efficiency, sim-to-real transfer, embedded latency, cybersecurity, privacy, and standards alignment. The resulting taxonomy is intended to clarify where AI is already useful as an engineering support tool and where further validation is needed before autonomous or safety-critical deployment.

eess.SY↗

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

Mixture-of-Experts (MoE) architecture offers enhanced efficiency for Large Language Models (LLMs) with modularized computation, yet its inherent sparsity poses significant hardware deployment challenges, including memory locality issues, communication overhead, and inefficient computing resource utilization. Inspired by the modular organization of the human brain, we propose Mozart, a novel algorithm-hardware co-design framework tailored for efficient training of MoE-based LLMs on 3.5D wafer-scale chiplet architectures. On the algorithm side, Mozart exploits the inherent modularity of chiplets and introduces: (1) an expert allocation strategy that enables efficient on-package all-to-all communication, and (2) a fine-grained scheduling mechanism that improves communication-computation overlap through streaming tokens and experts. On the architecture side, Mozart adaptively co-locates heterogeneous modules on specialized chiplets with a 2.5D NoP-Tree topology and hierarchical memory structure. Evaluation across three popular MoE models demonstrates significant efficiency gains, enabling more effective parallelization and resource utilization for large-scale modularized MoE-LLMs.

cs.AR↗

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference

Mixture-of-experts (MoE) architectures could achieve impressive computational efficiency with expert parallelism, which relies heavily on all-to-all communication across devices. Unfortunately, such communication overhead typically constitutes a significant portion of the total runtime, hampering the scalability of distributed training and inference for modern MoE models (consuming over $40\%$ runtime in large-scale training). In this paper, we first define collaborative communication to illustrate this intrinsic limitation, and then propose system- and algorithm-level innovations to reduce communication costs. Specifically, given a pair of experts co-activated by one token, we call them "collaborated", which comprises $2$ cases as intra- and inter-collaboration, depending on whether they are kept on the same device. Our pilot investigations reveal that augmenting the proportion of intra-collaboration can accelerate expert parallelism at scale. It motivates us to strategically optimize collaborative communication for accelerated MoE training and inference, dubbed Occult. Our designs are capable of either delivering exact results with reduced communication cost or controllably minimizing the cost with collaboration pruning, materialized by modified fine-tuning. Comprehensive experiments on various MoE-LLMs demonstrate that Occult can be faster than popular state-of-the-art inference or training frameworks (more than $1.5\times$ speed up across multiple tasks and models) with comparable or superior quality compared to the standard fine-tuning. Code is available at $\href{https://github.com/UNITES-Lab/Occult}{https://github.com/UNITES-Lab/Occult}$.

cs.LG↗

LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Load

Information on the web, such as scientific publications and Wikipedia, often surpasses users' reading level. To help address this, we used a self-refinement approach to develop a LLM capability for minimally lossy text simplification. To validate our approach, we conducted a randomized study involving 4563 participants and 31 texts spanning 6 broad subject areas: PubMed (biomedical scientific articles), biology, law, finance, literature/philosophy, and aerospace/computer science. Participants were randomized to viewing original or simplified texts in a subject area, and answered multiple-choice questions (MCQs) that tested their comprehension of the text. The participants were also asked to provide qualitative feedback such as task difficulty. Our results indicate that participants who read the simplified text answered more MCQs correctly than their counterparts who read the original text (3.9% absolute increase, p<0.05). This gain was most striking with PubMed (14.6%), while more moderate gains were observed for finance (5.5%), aerospace/computer science (3.8%) domains, and legal (3.5%). Notably, the results were robust to whether participants could refer back to the text while answering MCQs. The absolute accuracy decreased by up to ~9% for both original and simplified setups where participants could not refer back to the text, but the ~4% overall improvement persisted. Finally, participants' self-reported perceived ease based on a simplified NASA Task Load Index was greater for those who read the simplified text (absolute change on a 5-point scale 0.33, p<0.05). This randomized study, involving an order of magnitude more participants than prior works, demonstrates the potential of LLMs to make complex information easier to understand. Our work aims to enable a broader audience to better learn and make use of expert knowledge available on the web, improving information accessibility.

cs.CL↗