From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents
cs.AI, cs.LG, q-bio.QM
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/INTOSYN/Aritheia_GPU_Test
Terminology
Sources
- Estimating Silent Data Corruption Rates Using a Two-Level Model
- Accuracy, Decision Risk, and Sampling Cost in Quantum Error Mitigation
- LLM-PRISM: Characterizing Silent Data Corruption from Permanent GPU Faults in LLM Training
- TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training
- Causal Attribution via Activation Patching
- Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents
- ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
- Agents' Overreliance on Unreliable Tools
- OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
- Gemma 3 Technical Report
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