CCTest · Blog
TRACE Aligns FP4 Training and Rollouts for MoE Reinforcement Learning
Reinforcement Learning
cctest.ai

TRACE Aligns FP4 Training and Rollouts for MoE Reinforcement Learning

TRACE addresses the mismatch between training and rollout quantization in reinforcement learning for MoE language models. It uses rollout-side quantization outcomes to guide training-side FP4 rounding and reports up to 5.4× rollout speedup while preserving performance close to BF16 rollouts.

Read more
CCTest · Blog
HERMES Turns Repository Components into Collaborative Coding Agents
Coding AI
cctest.ai
Coding AI

HERMES Turns Repository Components into Collaborative Coding Agents

HERMES introduces Dev-Primitives, pairing repository artifacts with resident language models so components can reason about their own implementation, communicate, and support localized revisions. The work suggests that better agent harnesses can improve software engineering efficiency without relying only on larger models.

Read more