GSAR is a grounding-evaluation framework for multi-agent LLMs that uses a four-way claim typology, evidence-weighted asymmetric scoring, and tiered recovery decisions to detect and mitigate hallucinations.
Roy et al
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
RCLAgent uses multi-agent recursion-of-thought with parallel reasoning on trace graphs to outperform prior methods in root cause localization accuracy and efficiency for microservice systems.
EventADL introduces the first open-box framework for detecting anomalies and localizing root causes in cloud event data by learning semantic and frequency patterns from unlabeled historical events.
citing papers explorer
-
GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs
GSAR is a grounding-evaluation framework for multi-agent LLMs that uses a four-way claim typology, evidence-weighted asymmetric scoring, and tiered recovery decisions to detect and mitigate hallucinations.
-
Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought
RCLAgent uses multi-agent recursion-of-thought with parallel reasoning on trace graphs to outperform prior methods in root cause localization accuracy and efficiency for microservice systems.
-
EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems
EventADL introduces the first open-box framework for detecting anomalies and localizing root causes in cloud event data by learning semantic and frequency patterns from unlabeled historical events.