← Search

Haotong Sun

2 accepted papers

2026

BRIDGE: Triangular Fixed-Point Refinement for Long-Horizon Persona Consistency

ICML 2026poster

Long-horizon dialogue agents suffer from *latent state drift*: what an agent says, what it internally represents, and what it stores in memory can diverge silently across turns. This creates *asymmetric rupture risk*—many locally coherent exchanges undone by a single high-cost contradiction. We prop…

Cited by 0SourceScholar
2026

Know Thyself, Know Thy User: Intrinsic Dual-Perspective Reasoning for Role-Playing LLMs

ICML 2026poster

As role-playing Large Language Models (LLMs) become central to personalized AI, they face a fundamental challenge: balancing character authenticity with user satisfaction. Prior dual-process and dual-perspective approaches address this through prompt-level conditioning, auxiliary modules, or inferen…

Cited by 0SourceScholar