Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
cs.AI, cs.SE
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Program Synthesis with Large Language Models
- Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Evaluating Large Language Models Trained on Code
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- GLM-5: from Vibe Coding to Agentic Engineering
- Measuring Coding Challenge Competence With APPS
- Instruction Following without Instruction Tuning
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- Compression Represents Intelligence Linearly
- On Predicting the Post-training Potential of Pre-trained LLMs
- APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training
- Gemma 4 Technical Report
- Kimi K2: Open Agentic Intelligence
- Kimi K3: Open Frontier Intelligence
- The Invisible Leash: Why RLVR May or May Not Escape Its Origin
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation 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
- Agents' Last Exam
- 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