Get Started
Topic · 29 recaps

Code Generation & Program Synthesis

Models that write, edit, and reason about source code — from autocomplete to autonomous coding agents, plus evaluation suites and execution-based training.
PostsQuestions
Home
Topics
Search
Library
Sort
Newest
$Φ$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Agents · Sep 9
$τ^τ$-Bench: An Environment for End-To-End, Realistic Agent Construction
Agents · Sep 4
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Code Generation · Sep 3
Editable Visual Design
Code Generation · Sep 3
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Agents · Sep 3 · 7:24
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Code Generation · Sep 3 · 8:23
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
Code Generation · Sep 2 · 6:50
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Agents · Sep 2
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Agents · Sep 2 · 7:00
Dr. Claw: An AI Scientist Workspace for Vibe Research
Agents · Aug 31