F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/henrique-polybee/f3-agi-v4
Terminology
Sources
- The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
- Mistake gating leads to energy and memory efficient continual learning
- Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
- ARC-AGI Without Pretraining
- On the Measure of Intelligence
- ARC Prize 2025: Technical Report
- Ambiguous Fits: The Rashomon Effect and Challenges in Scaling Law Estimation
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
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