CCTest · Blog
Do Coding Agents Understand Repositories—or Just Recognize Them?
Evaluation & Benchmarks
cctest.ai

Do Coding Agents Understand Repositories—or Just Recognize Them?

A study introduces SchrodingerRepo, a dynamic evaluation framework designed to test whether coding agents can solve repository-level tasks without relying on familiar project cues. Its results suggest that static benchmarks may reward more than general software engineering ability.

Read more
CCTest · Blog
LatentPort Tests Cross-Model Memory Handoffs Beyond KV Cache
Memory & Context
cctest.ai
Memory & Context

LatentPort Tests Cross-Model Memory Handoffs Beyond KV Cache

LatentPort investigates whether a larger hybrid language model can inherit a smaller model’s live inference state without replaying the historical prefix. In a Qwen3.5 4B-to-9B experiment, transferring recurrent and convolutional state alongside translated KV cache substantially narrowed the gap to native 9B inference.

Read more