2 papers
cs.CR2026
Heterogeneous LLM Debate Under Adversarial Peers: Honest Gains, Replacement Costs, and Resilience
Prashanti Nilayam, Kiran Kumar Ramanna, Prashil Tumbade +1
Heterogeneous LLM debate is motivated by the promise that diverse peers correct one another, but the same exchange that carries correction also carries adversarial influence. We me…
cs.MA2026
Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines
Prashanti Nilayam, Kiran Ramanna, Prashil Tumbade
Multi-stage LLM pipelines that perform multi-agent debate, intrinsic self-correction, or retrieval-augmented verification exhibit puzzling aggregate behaviors: accuracy plateaus an…