Learning Individual Scientific Taste with Privileged Hindsight Distillation
cs.AI, cs.LG
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AI Can Learn Scientific Taste
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
- DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
- A Measure of Research Taste
- LLMs learn scientific taste from institutional traces across the social sciences
- ReviewGuard: Aligning LLM-Assisted Peer Review with Long-Term Scientific Impact
- OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
- Measuring the Gap Between Human and LLM Research Ideas
- An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop
- Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
- The Design Space of Recent AI-assisted Research Tools for Ideation, Sensemaking, and Scientific Creativity
- LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
- HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
- APRES: An Agentic Paper Revision and Evaluation System
- On the Limits of LLM-as-Judge for Scientific Novelty Assessment
- Unifying distillation and privileged information
- Self-Distilled RLVR
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
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