Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
cs.AI
Submitted: 2026-05-24
Updated: 2026-11-06
Code: https://github.com/arcprize/ARC-AGI-2
Terminology
Sources
- Parameter-Efficient Quality Estimation via Frozen Recursive Models
- Adaptive Computation Time for Recurrent Neural Networks
- Less is More: Recursive Reasoning with Tiny Networks
- Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
- Test-time Adaptation of Tiny Recursive Models
- Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
- Steering Language Models With Activation Engineering
- Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
- Scaling Latent Reasoning via Looped Language Models
- A Physical Unclonable Function Based on Variations of Write Times in STT-MRAM due to Manufacturing Defects
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