Metacognitive Steering: Learning the Structure of Scientific Judgment
cs.AI
Submitted: 2026-09-14
Updated: 2026-09-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Concept Heterogeneity-aware Representation Steering
- Singular Value Decomposition and Neural Networks
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V3 Technical Report
- Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering
- Contextual Linear Activation Steering of Language Models
- Prototype-Based Dynamic Steering for Large Language Models
- COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning
- Programming Refusal with Conditional Activation Steering
- Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
- Prompt Optimization with Human Feedback
- AI scientists produce results without reasoning scientifically
- Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
- Steering Language Models With Activation Engineering
- Understanding Reasoning in Thinking Language Models via Steering Vectors
- Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning
- Generalization or Memorization: Dynamic Decoding for Mode Steering
- Representation Engineering: A Top-Down Approach to AI Transparency
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection