3 papers
cs.AI2026
Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination
Ruitong Li, Binjie Guo, Aisheng Mo +3
Heterogeneous language-model ensembles expand the space of candidate responses, yet they lack a principled criterion for when a newly generated answer should supersede an already s…
cs.SE2026
The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals
Ruitong Li, Binjie Guo, Aisheng Mo +4
Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software. Prompt-driven "vibe…
cs.LG2026
When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero
Ruitong Li, Aisheng Mo, Guowei Su +10
AlphaZero is normally evaluated as one agent: a policy-value network fused with Monte Carlo tree search. That fusion hides a causal question. When self-play search is given a usefu…