Minxing Wang

Minxing Wang, Xiaofei Xie, Yintong Huo

Agentic systems have been widely studied to automate software engineering jobs such as bug fixing. As these systems increasingly tackle complex tasks, understanding where and why they fail becomes essential for iterative refinement and operational reliability. Existing automated failure diagnosis approaches leverage task execution trajectories, yet their effectiveness degrades substantially as trajectory length and complexity increase. For repository-level coding tasks specifically, trajectories are laden with noise, such as redundant program structure and verbose code context. Moreover, these trajectories are very long, while long-context reasoning remains a known weakness of LLMs. To address these two challenges, we propose TrajAudit, the first failure diagnosis framework for repository-level coding trajectories. TrajAudit employs an investigator agent supported by two modules: one filters failure-irrelevant information through pattern matching and keyword detection, and the other generates a preliminary diagnosis from test failure reports as prior knowledge, helping the agent handle noisy long contexts. The investigator agent can further invoke tools to retrieve filtered content on demand, ensuring that critical information is preserved while noise is minimized. We also introduce RootSE, a benchmark of 93 real-world agentic failure instances sourced from software maintenance tasks, representing the most complex trajectory diagnosis benchmark to date. Experiments on RootSE show that TrajAudit outperforms all existing baselines by over 24.4 percentage points in localization accuracy, while reducing token consumption by at least 18%, demonstrating its practical effectiveness. We hope this work draws community attention to failure management in agentic software engineering and provides a foundational resource for future research.

Shiwen Shan, Yintong Huo, Minxing Wang et al.

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%.

Minxing Wang, Yintong Huo

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.