MASPrism attributes failures in multi-agent systems by ranking candidates from prefill-stage NLL and attention signals of a 0.6B SLM, beating baselines by up to 33.41% Top-1 accuracy and proprietary LLMs by up to 89.5% relative improvement while processing traces in 2.66 seconds.
Empirical evaluation of the Tarantula automatic fault-localization technique,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Holmes is a multimodal multi-agent system using a hierarchical Retrieve-Explore-Reason architecture to automate root cause analysis of mobile crashes, achieving 87.6% function-level accuracy and 98% time reduction on real WeChat data.
A systematic mapping study of 248 papers introduces a taxonomy of synergistic effects, inter-analysis workflows, and mapping functions to catalog patterns in combined program analysis techniques.
Debugging tools should present execution history in time order to support better hypothesis generation about program behavior.
Empirical evaluation of augmenting statistical fault localization with execution features extracted by EFDD and mapped via random-forest importances on Tests4Py subjects.
citing papers explorer
-
MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals
MASPrism attributes failures in multi-agent systems by ranking candidates from prefill-stage NLL and attention signals of a 0.6B SLM, beating baselines by up to 33.41% Top-1 accuracy and proprietary LLMs by up to 89.5% relative improvement while processing traces in 2.66 seconds.
-
Holmes: Multimodal Agentic Diagnosis for Mixed-Language Mobile Crashes at Industrial Scale
Holmes is a multimodal multi-agent system using a hierarchical Retrieve-Explore-Reason architecture to automate root cause analysis of mobile crashes, achieving 87.6% function-level accuracy and 98% time reduction on real WeChat data.
-
Combined Program Analysis Techniques: A Systematic Mapping Study
A systematic mapping study of 248 papers introduces a taxonomy of synergistic effects, inter-analysis workflows, and mapping functions to catalog patterns in combined program analysis techniques.
-
Tracers for debugging and program exploration
Debugging tools should present execution history in time order to support better hypothesis generation about program behavior.
-
How do Execution Features Improve Statistical Fault Localization? An Empirical Study
Empirical evaluation of augmenting statistical fault localization with execution features extracted by EFDD and mapped via random-forest importances on Tests4Py subjects.