Sahaj.blogs

Day page

2 Dec 2025

Paper summary

Paper summary: From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence

A large survey and practical guide to code LLMs, from data curation and pre-training through SFT, RL and coding agents, comparing general and code-specialised models and the gap between benchmarks and real development.

  • The guide follows the whole life cycle of a code model, from data to agents, with its own probing experiments.
  • It highlights the gap between academic benchmarks and real-world needs: correctness, security, large-codebase context and tool integration.

Read the post →