Agentic AI

CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
Scalable oversight via confidence-guided reasoning; enables safe self-correction matching parallel decoding accuracy at orders-of-magnitude lower compute.
Chen Jin, Ryutaro Tanno, Tom Diethe, Philip Teare
CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
Dynamic Mixture of Agents (DMoA)
A test-time LLM ensembling strategy that dynamically adapts to balance performance, diversity, and consistency, achieving state-of-the-art results.
Abdullah Abdulaal, Chen Jin, Nina Montaña-Brown, Aryo Pradipta Gema, Daniel C Castro, Daniel C Alexander, Philip Teare, Tom Diethe, Dino Oglic, Amrutha Saseendran
Dynamic Mixture of Agents (DMoA)