Weida Liang

Weak interactive feedback can dynamically steer LLMs to the correct similarity criterion for test-time decisions, unlocking significant performance gains beyond static mixtures.

LLM agents can now dynamically curate multimodal memory on-demand, achieving optimal performance-cost-latency trade-offs by intelligently choosing between pre-computed and runtime-generated evidence.

Human-written solutions can actually *hurt* model performance on math problems, highlighting a critical gap between strategy usage and executability that Selective Strategy Retrieval (SSR) effectively bridges.