arXiv AI
Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 2
Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
arXiv:2601.22984v3 Announce Type: replace Abstract: Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evalu...
arXiv AI
Sep 10
SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores
arXiv:2609.06192v1 Announce Type: new Abstract: Scientific coding agents produce interdependent code, results, figures, and claims, yet evaluating final outputs alone does not establish whether the...
arXiv AI
Aug 21
Hallucination as a Feature, not a Defect: Evaluating a multi-agent architecture to transform speculative language-model outputs into testable scientific hypotheses
arXiv:2608. 19206v1 Announce Type: cross Abstract: Contemporary Large Language Models (LLMs) are increasingly aligned to suppress hallucinations, prioritizing factual retrieval over combinatorial creativity.
arXiv AI
3d ago
DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?
arXiv:2609.33357v2 Announce Type: replace Abstract: Reliable automated research requires agents to vet data, verify analyses, and generate hypotheses grounded in trustworthy evidence, potentially red...
arXiv Computation and Language
Aug 31
Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs
arXiv:2606.21359v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to communicate and explain scientific concepts, yet their tendency to hallucinate poses signific...
arXiv AI
Sep 7
GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion
The paper introduces GRACE, a framework that breaks down large language model (LLM) responses into atomic claims and grounds them against trusted knowledge priors using a weighted bipartite graph. Edge weights enable weighted centrality analysis to classify claims as Grounded, Refuted, or Boundary, identifying hallucinations and frontier knowledge. An objective called Return on Attention (RoA) prioritizes expert review only for high‑uncertainty claims, and verified claims become new evidence anchors, creating a loop that expands the knowledge base across iterations.