Beyond fabrication: Misattributed numbers in papers written by AI research agents
cs.AI, cs.CL, cs.DL
Submitted: 2026-10-28
Updated: 2026-10-31
Comments: v2: corrected author names; clarified the second-judge comparison and two table captions. 43 pages, 5 figures, 13 tables. Code and data: https://github.com/mos3b-faqeeh/agent-integrity-analysis
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents