Get Started
Home
Topics
Search
Library
Topic · 16 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.
Play latest
...
Sort
Newest
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
Agents · Aug 28
0
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Agents · Aug 20
0
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis
Agents · Aug 19
0
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Agents · Aug 10
0
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Agents · Aug 7
0
Recursive Synthesis for Long-Horizon Terminal Tasks
Agents · Aug 5
0
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
Agents · Jul 28
0
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Code Generation · Jul 20
0
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Agents · Jul 18
0
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Agents · Jul 14
0