Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, and choose valid actions under changing constraints. We study this setting in the LM Playschool Challenge with a 2B open-weight model, and find that many failures are not only broad knowledge failures but also local decision failures: repeated guesses, malformed actions, and violations of feedback that the model has just seen. These diagnostics motivate a training recipe organized around three steps: acquire broad game participation through supe
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) · 87%NirDiamant/GenAI_Agents →
“Fuzzy title match (0.94): “Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training ” ≈ “NirDiamant/GenAI_Agents””
- FuzzySimilar title/name (fuzzy) · 84%Unity-Technologies/ml-agents →
“Fuzzy title match (0.92): “Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training ” ≈ “Unity-Technologies/ml-agents””
- FuzzySimilar title/name (fuzzy) · 59%datawhalechina/hello-agents →
“Fuzzy title match (0.73): “Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training ” ≈ “datawhalechina/hello-agents””
- FuzzySimilar title/name (fuzzy) · 59%Eigenwise/atomic-agents →
“Fuzzy title match (0.73): “Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training ” ≈ “Eigenwise/atomic-agents””
- FuzzySimilar title/name (fuzzy) · 59%jnMetaCode/agency-agents-zh →
“Fuzzy title match (0.73): “Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training ” ≈ “jnMetaCode/agency-agents-zh””
- LinkedLinked via arxiv author · 85%Nan Li →
“Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents”