What Output-Only Review Cannot Verify: Study Contracts for Research Agents

cs.AI

Submitted: 2026-10-08

Updated: 2026-10-08

Comments: 15 pages, 4 tables. Preprint. Not peer reviewed. Companion manuscripts prepared in parallel

Code: https://github.com/AlgorithmicResearchGroup/deltaml-bench-vivaria

Project page: https://apodexai.github.io/FrontierAgent/benchmarks/FrontierChallenge

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims
• AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
• Concrete Problems in AI Safety
• FrontierChallenge: Evaluating Scientific Workflow Completion
• ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations
• Inspectable AI for Science: A Research Object Approach to Generative AI Governance

Related papers

• 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
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems