AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
cs.LG, cs.AI
Submitted: 2025-10-13
Updated: 2026-08-25
Terminology
Sources
- Phi-4 Technical Report
- Phi-4-reasoning Technical Report
- Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
- Thought Anchors: Which LLM Reasoning Steps Matter?
- Truth is Universal: Robust Detection of Lies in LLMs
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Talk like a Graph: Encoding Graphs for Large Language Models
- Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Language Models Represent Space and Time
- Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations
- Imagining and building wise machines: The centrality of AI metacognition
- Evaluating the Robustness of Analogical Reasoning in Large Language Models
- Are self-explanations from Large Language Models faithful?
- When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Open Problems in Mechanistic Interpretability
- Analyzing the Structure of Attention in a Transformer Language Model
- Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks