From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
cs.AI
Submitted: 2026-06-16
Updated: 2026-08-26
Code: https://github.com/euyis1019/llm-brewing
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
- Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
- Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
- CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
- On Calibration of Modern Neural Networks
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- Universal Neurons in GPT2 Language Models
- Overthinking the Truth: Understanding how Language Models Process False Demonstrations
- Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
- Qwen2.5-Coder Technical Report
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Language Models (Mostly) Know What They Know
- CodeMind: Evaluating Large Language Models for Code Reasoning
- Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
- Qwen3 Technical Report
- Mixture-of-Depths: Dynamically allocating compute in transformer-based 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
- 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