R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning

• URL: http://arxiv.org/abs/2509.25987v1
• Date: Tue, 30 Sep 2025 09:19:31 GMT
• Title: R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
• Authors: Yilun Liu, Ziang Chen, Song Xu, Minggui He, Shimin Tao, Weibin Meng, Yuming Xie, Tao Han, Chunguang Zhao, Jingzhou Du, Daimeng Wei, Shenglin Zhang, Yongqian Sun,
• Abstract summary: R-Log is a novel reasoning-based paradigm that mirrors the structured, step-by-step analytical process of human engineers.<n>R-Log is first cold-started on a curated dataset of 2k+ reasoning trajectories, guided by 13 strategies from manual O&M practices.<n> Empirical evaluations on real-world logs show that R-Log outperforms existing methods across five log analysis tasks.
• Score: 19.713020881817588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing complexity of log data in modern software systems has prompted the use of Large Language Models (LLMs) for automated log analysis. Current approaches typically rely on direct supervised fine-tuning (SFT) on log-label pairs. However, this exacerbates the domain discrepancy between general-purpose LLMs and specialized log data, causing overfitting. Furthermore, SFT's imbalanced loss computation often allows lengthy contexts to overwhelm critical, concise details in model answers, leading to hallucinations. To address these limitations, we propose R-Log, a novel reasoning-based paradigm that mirrors the structured, step-by-step analytical process of human engineers. This approach enhances generalizability by learning the underlying rules behind conclusions. We further employ Reinforcement Learning (RL) to optimize the model within a simulated O&M environment, thereby reducing hallucinations by directly rewarding correct outcomes. R-Log is first cold-started on a curated dataset of 2k+ reasoning trajectories, guided by 13 strategies from manual O&M practices, to establish an initial reasoning capability. This ability is then refined via RL using a joint reward function. Empirical evaluations on real-world logs show that R-Log outperforms existing methods across five log analysis tasks, particularly in unseen scenarios (by 228.05%). We also designed R-Log-fast with 5x speedup while keeping 93% of the efficacy.

Related papers

• LogSieve: Task-Aware CI Log Reduction for Sustainable LLM-Based Analysis [0.0]
  We present LogSieve, a lightweight, RCA-aware and semantics-aware log reduction technique.<n>We evaluate it on CI logs from 20 open-source Android projects using GitHub Actions.<n>It achieves an average 42% reduction in lines and 40% reduction in tokens with minimal semantic loss.
  arXiv  Detail & Related papers  (2026-01-28T00:49:50Z)
• Training LLMs with LogicReward for Faithful and Rigorous Reasoning [75.30425553246177]
  We propose LogicReward, a reward system that guides model training by enforcing step-level logical correctness with a theorem prover.<n>An 8B model trained on data constructed with LogicReward surpasses GPT-4o and o4-mini by 11.6% and 2% on natural language inference and logical reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-20T03:43:02Z)
• Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction [0.0]
  Large Language Models (LLMs) are increasingly used to generate explanations of process models discovered from event logs.<n>This paper reports an evaluation of explanation quality under progressive behavioral-input reduction.<n>On synthetic logs, explanation quality is largely preserved under moderate reduction, indicating a practical cost-quality trade-off.
  arXiv  Detail & Related papers  (2025-10-10T13:10:50Z)
• MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization [103.74675519953898]
  Long-chain reflective reasoning is a prerequisite for solving complex real-world problems.<n>We build a benchmark consisting 1,260 samples of 42 challenging synthetic tasks.<n>We generate post-training data and explore learning paradigms for exploiting such data.
  arXiv  Detail & Related papers  (2025-10-09T17:53:58Z)
• Making Mathematical Reasoning Adaptive [61.45161826629692]
  We propose the AdaR framework to enable adaptive reasoning in large language models (LLMs)<n>AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic.<n> Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning.
  arXiv  Detail & Related papers  (2025-10-06T09:30:05Z)
• Pushing LLMs to Their Logical Reasoning Bound: The Role of Data Reasoning Intensity [59.27594125465172]
  We introduce Data Reasoning Intensity (DRI), a novel metric that quantifies the latent logical reasoning complexity of samples.<n>We then introduce a re-cognizing optimization strategy that systematically enhances the logical reasoning intensity of training data.
  arXiv  Detail & Related papers  (2025-09-29T14:20:04Z)
• LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis [66.79746720402811]
  General-purpose large language models (LLMs) struggle to formulate structured reasoning that align with expert cognition and deliver precise details of reasoning steps.<n>We propose LogReasoner, a coarse-grained enhancement framework designed to enable LLMs to reason log analysis tasks like experts.<n>We evaluate LogReasoner on four distinct log analysis tasks using open-source LLMs such as Qwen-2.5 and Llama-3.
  arXiv  Detail & Related papers  (2025-09-25T06:26:49Z)
• System Log Parsing with Large Language Models: A Review [2.2779174914142346]
  Large language models (LLMs) have introduced the new research field of LLM-based log parsing.<n>Despite promising results, there is no structured overview of the approaches in this relatively new research field.<n>This work systematically reviews 29 LLM-based log parsing methods.
  arXiv  Detail & Related papers  (2025-04-07T09:41:04Z)
• AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model [42.72663245137984]
  This paper introduces an adaptive log analysis framework known as AdaptiveLog.<n>It effectively reduces the costs associated with LLM while ensuring superior results.<n>Experiments demonstrate that AdaptiveLog achieves state-of-the-art results across different tasks.
  arXiv  Detail & Related papers  (2025-01-19T12:46:01Z)
• Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge [22.355668420639475]
  Log analysis represents a critical sub-domain within AI applications.<n>Existing solutions using large language models (LLMs) show promise, but they are limited by a significant domain gap between natural and log languages.<n>We present a domain adaptation approach that addresses these limitations by integrating interpretable domain knowledge into open-source LLMs.
  arXiv  Detail & Related papers  (2024-12-02T11:05:31Z)
• LogLM: From Task-based to Instruction-based Automated Log Analysis [22.44842963552044]
  Existing approaches mostly treat log analysis as training a model to perform an isolated task.<n>We propose an instruction-based training approach that transforms log-label pairs into a unified format of instruction-response pairs.<n>Our trained model, LogLM, can follow complex user instructions and generalize better across different tasks.
  arXiv  Detail & Related papers  (2024-10-12T03:36:52Z)
• LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models [19.657278472819588]
  We introduce Log-LLM, a novel log integrated with LLM capabilities. We address the intricate challenge of parsing granularity, proposing a new metric to allow users to calibrate granularity to their specific needs. Our method's efficacy is empirically demonstrated through evaluations on the Loghub-2k and the large-scale LogPub benchmark.
  arXiv  Detail & Related papers  (2024-08-25T05:34:24Z)
• LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models [63.14196038655506]
  We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) Our methodology reveals significant gaps in LLMs' learning of logical rules, with identified reasoning failures ranging from 29% to 90% across different models. We leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5%.
  arXiv  Detail & Related papers  (2024-01-01T13:53:53Z)
• Self-Supervised Log Parsing [59.04636530383049]
  Large-scale software systems generate massive volumes of semi-structured log records. Existing approaches rely on log-specifics or manual rule extraction. We propose NuLog that utilizes a self-supervised learning model and formulates the parsing task as masked language modeling.
  arXiv  Detail & Related papers  (2020-03-17T19:25:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.