Disclosure-Gated User Simulation for Companion-Agent Evaluation
Using a large language model to play the user is now standard in scalable evaluation. It has a repeatedly diagnosed failure: the simulated user is excessively cooperative, so a system under test can score by the sheer number of questions it asks rather than by making the user willing to speak. We answer with a disclosure gate conditioning information release on the companion agent's behaviour: its state is a ladder of five ordered gates, merged onto three observable depth layers. We specify, ablate, and audit it, and train a user simulator against that specification. Gating behaviour is learne
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “Disclosure-Gated User Simulation for Companion-Agent Evaluat” ≈ “AgentCore-8B””
- LinkedLinked via arxiv author · 85%Yiyao Liu →
“Disclosure-Gated User Simulation for Companion-Agent Evaluation”
- LinkedLinked via arxiv author · 85%Yu He →
“Disclosure-Gated User Simulation for Companion-Agent Evaluation”
- FuzzySimilar title/name (fuzzy) · 59%iflytek/astron-agent →
“Fuzzy title match (0.73): “Disclosure-Gated User Simulation for Companion-Agent Evaluat” ≈ “iflytek/astron-agent””
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “Disclosure-Gated User Simulation for Companion-Agent Evaluat” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “Disclosure-Gated User Simulation for Companion-Agent Evaluat” ≈ “zhayujie/CowAgent””
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “Disclosure-Gated User Simulation for Companion-Agent Evaluat” ≈ “NousResearch/hermes-agent””