Qwen3.5
2 articles in the last 30 days.
-
BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model
Tether AI Research released BotPsy, a 0.8B-parameter function-calling model built on Qwen3.5-0.8B for on-device agents. It roughly doubles the base model's scores on BFCL v4, ACEBench and τ-bench.
-
Your Experts Have Partners. There's HOPE for Keeping Them Together
HOPE is a second-order expert pruning method for Mixture-of-Experts models that accounts for pairwise interactions between experts. At 50% pruning it gets the best average rank and up to +6.1% on agentic coding tasks.