Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/CherYou/AutoResearchBench
Sources
- OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
- BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
- Inference-Time Budget Control for LLM Search Agents
- AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking
- PaSa: An LLM Agent for Comprehensive Academic Paper Search
- AI Agents That Matter
- Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
- SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents
- AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
- RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
- Language agents achieve superhuman synthesis of scientific knowledge
- AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
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