SDVDiag integrates RLHF and context pruning to raise causal edge detection precision from 14% to 100% in an automated valet parking test, outperforming purely data-driven methods.
arXiv preprint arXiv:2408.00803 (2024)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
TopoEvo is a topology-aware self-evolving multi-agent framework for root cause analysis in microservices that uses multimodal alignment, vector-quantized symptom tokens, and a hypothesis-evidence-test workflow to separate root causes from cascading symptoms.
LATS-RCA applies multi-agent Language Agent Tree Search to automate root cause analysis in microservices, reporting high accuracy on a small open-source Java system but lower accuracy in a complex production environment.
PropLLM combines hop-by-hop scene reconstruction with LLMs for network fault diagnosis, reporting 3.9% and 4.7% accuracy gains plus 50.8% hallucination reduction on real datasets.
OPS CORTEX uses four-tier operational memory to deterministically derive root causes from topology and timing before applying LLMs for explanation in microservice failures.
Presents a causality-driven multi-objective optimization method for microservice placement that uses necessary and sufficient conditional probabilities of interference estimated from profiling to reduce performance degradation.
citing papers explorer
-
SDVDiag: Using Context-Aware Causality Mining for the Diagnosis of Connected Vehicle Functions
SDVDiag integrates RLHF and context pruning to raise causal edge detection precision from 14% to 100% in an automated valet parking test, outperforming purely data-driven methods.
-
TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices
TopoEvo is a topology-aware self-evolving multi-agent framework for root cause analysis in microservices that uses multimodal alignment, vector-quantized symptom tokens, and a hypothesis-evidence-test workflow to separate root causes from cascading symptoms.
-
Multi-Agent Systems for Root Cause Analysis in Microservices
LATS-RCA applies multi-agent Language Agent Tree Search to automate root cause analysis in microservices, reporting high accuracy on a small open-source Java system but lower accuracy in a complex production environment.
-
PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis
PropLLM combines hop-by-hop scene reconstruction with LLMs for network fault diagnosis, reporting 3.9% and 4.7% accuracy gains plus 50.8% hallucination reduction on real datasets.
-
A Topology-Aware, Memory-Centric Architecture that Separates Root-Cause Derivation from Root-Cause Explanation
OPS CORTEX uses four-tier operational memory to deterministically derive root causes from topology and timing before applying LLMs for explanation in microservice failures.
-
Interference-Aware Cross-Application Placement: A Multi-Objective Optimization Approach for Microservice Clusters
Presents a causality-driven multi-objective optimization method for microservice placement that uses necessary and sufficient conditional probabilities of interference estimated from profiling to reduce performance degradation.