Tag
This paper identifies KV-cache contamination as a failure mode for activation steering in dialogue and proposes GCAD, a method that extracts steering signals from prompt contributions and applies token-level gating to improve long-horizon coherence, achieving substantial gains on multi-turn benchmarks.
Developer reports that small-active-parameter MOE models like qwen3.6-35b-A3b exhibit lower coherence and require more guidance than dense qwen3.5-27b, making them hard to slot into agentic workflows.