Introduces unified span-level hallucination detection benchmark over code, tool output, and documents; fine-tuned Qwen3.5-2B reaches 0.689 span-F1 and outperforms baselines including on code-agent data.
AgentHallu: Benchmarking automated hallucination attribution of LLM-based agents
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 8roles
background 3representative citing papers
Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
Turkish speakers show a robust preference for -DI in high-trust contexts and -mIs in low-trust contexts, while LLMs exhibit inconsistent, often reversed, or base-rate-driven behavior.
Context drift between agents causes hallucinations in multi-agent LLMs; the Shared State Verification Protocol reduces them more effectively than full-broadcast synchronization with 58% fewer API calls.
Bounded autonomy using typed action contracts and consumer-side execution lets LLMs safely operate enterprise systems, achieving 23 of 25 tasks with zero unsafe executions versus 17 for unconstrained AI across 25 trials.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
citing papers explorer
-
Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents
Introduces unified span-level hallucination detection benchmark over code, tool output, and documents; fine-tuned Qwen3.5-2B reaches 0.689 span-F1 and outperforms baselines including on code-agent data.
-
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
-
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
-
Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation
Turkish speakers show a robust preference for -DI in high-trust contexts and -mIs in low-trust contexts, while LLMs exhibit inconsistent, often reversed, or base-rate-driven behavior.
-
Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems
Context drift between agents causes hallucinations in multi-agent LLMs; the Shared State Verification Protocol reduces them more effectively than full-broadcast synchronization with 58% fewer API calls.
-
Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution
Bounded autonomy using typed action contracts and consumer-side execution lets LLMs safely operate enterprise systems, achieving 23 of 25 tasks with zero unsafe executions versus 17 for unconstrained AI across 25 trials.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
- Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents