arXiv subjects

Minxing Wang

Publications and source records attributed to Minxing Wang.

4 recordsLinked to original sources

arXiv2026

Time Series Forecasting based on Solana Digital Asset Dataset

Accurate analysis and forecasting of Solana digital assets require data that captures both token-level behavior and ecosystem-level DEX activity. This paper introduces, to the best of our knowledge, the first Solana digital asset time series dataset designed for forecasting and market-structure analysis. The dataset contains 1,584 tokens observed at daily resolution from March 24, 2024 to March 16, 2025, with 27 variables combining token transactions, prices, liquidity-pool balances, trader activity, Solana DEX volume, DEX trader counts, newly created pairs, and SOL price indicators. Rather than treating the dataset only as input for model comparison, we use it to characterize the DEX-driven token market during a period of rapid ecosystem growth. The analysis identifies synchronized market-wide activity peaks in mid-November 2024 and mid-January 2025 across DEX volume, token trading volume, active wallets, buyers, sellers, new traders, liquidity-pool balances, and SOL price. The January 2025 peak coincides with the 'Trump' token event and is accompanied by a visible transition from liquidity accumulation to withdrawals, suggesting that individual token dynamics are strongly coupled to broader Solana market sentiment and DEX activity. Forecasting experiments are then used as an empirical validation of the dataset's signal content. In three-day-ahead market-capitalization prediction, PatchTST achieves the best overall rank, fine-tuned Chronos follows closely, and statistical baselines remain competitive for trend-dominated tokens. Feature-importance analysis further shows that SOL price, SOL moving averages, total DEX volume, DEX trader counts, and newly created pairs are among the most informative covariates. The main contribution is therefore a curated Solana forecasting dataset and a data-driven analysis of the ecosystem-level factors that shape token volatility.

cs.CE↗

arXiv2026

TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems

Agentic systems have been widely studied to automate coding tasks such as bug fixing and feature implementation. As these systems increasingly operate on complex codebases, understanding where and why they fail becomes essential for iterative refinement and operational reliability. Existing automated failure diagnosis approaches leverage \textit{task execution trajectories}, yet they struggle with trajectories produced by repository-level coding agents due to two key properties. First, these trajectories are often long, spanning many execution steps, making it difficult for LLMs to track the causal chain of failure over the execution history. Second, these trajectories are laden with noise, containing substantial low-signal observations such as redundant program structures and verbose code context, which can interfere with LLM reasoning. To address these challenges, we propose \textit{TrajAudit}, an automated failure diagnosis framework specifically for trajectories produced by repository-level coding agents. TrajAudit employs an investigator agent supported by two modules: one reduces failure-irrelevant noisy context through semantic saliency folding, and the other derives preliminary diagnostic guidance from test failure reports as prior knowledge to help LLMs focus on likely failure regions. The investigator agent can further invoke tools to inspect folded content on demand, enabling a focused investigation without losing access to the full trajectory context. We also introduce \textit{RootSE}, a benchmark of 102 real-world instances from repository-level coding tasks, each annotated with the earliest decisive error step and a justification. Experiments on RootSE show that TrajAudit outperforms the strongest baselines by 10.8\% and 21.6\% in exact failure localization accuracy in the with- and without-reference settings, respectively, demonstrating its effectiveness.

cs.SE↗

arXiv2026

CelerLog: Fast Log Parsing via Dynamic Routing

Log parsing is a fundamental step for automated log analysis, which transforms raw log messages into structured formats. Existing syntax-based parsers struggle with complex logs because they lack semantic reasoning ability. Emerging LLM-powered semantic parsers achieve high accuracy but suffer from prohibitive latency and token costs because they apply semantic inference across all logs. Our key observation is that not all logs necessitate complex semantic understanding: a vast majority of logs exhibit repetitive patterns that can be extracted via straightforward statistical analysis. Driven by this insight, we propose CelerLog, a fast and effective log parser. CelerLog introduces a dynamic routing mechanism to classify logs into dense and sparse groups. Logs with strong statistical patterns (dense groups) are processed by an efficient statistical processor, whereas the sparse groups lacking such patterns are routed to an LLM for semantic inference. This hybrid strategy avoids unnecessary LLM invocations. Extensive experiments on 14 public datasets show that CelerLog achieves leading performance over state-of-the-art baselines and is 7.9x to 18.6x faster than LLM methods and up to 1.5x faster than Drain. Additionally, it reduces costs by decreasing token consumption by 80.2% - 94.1% and LLM invocations by 86.4% - 90.9%.

cs.SE↗

arXiv2026

Small is Beautiful: A Practical and Efficient Log Parsing Framework

Log parsing is a fundamental step in log analysis, partitioning raw logs into constant templates and dynamic variables. While recent semantic-based parsers leveraging Large Language Models (LLMs) exhibit superior generalizability over traditional syntax-based methods, their effectiveness is heavily contingent on model scale. This dependency leads to significant performance collapse when employing smaller, more resource-efficient LLMs. Such degradation creates a major barrier to real-world adoption, where data privacy requirements and computational constraints necessitate the use of succinct models. To bridge this gap, we propose EFParser, an unsupervised LLM-based log parser designed to enhance the capabilities of smaller models through systematic architectural innovation. EFParser introduces a dual-cache system with an adaptive updating mechanism that distinguishes between novel patterns and variations of existing templates. This allows the parser to merge redundant templates and rectify prior errors, maintaining cache consistency. Furthermore, a dedicated correction module acts as a gatekeeper, validating and refining every LLM-generated template before caching to prevent error injection. Empirical evaluations on public large-scale datasets demonstrate that EFParser outperforms state-of-the-art baselines by an average of 12.5% across all metrics when running on smaller LLMs, even surpassing some baselines utilizing large-scale models. Despite its additional validation steps, EFParser maintains high computational efficiency, offering a robust and practical solution for real-world log analysis deployment.

cs.SE↗