7 papers
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Yuqi Wang, Fengyuan Liu, Haochen Luo +2
Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves o…
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Sichun Luo, Yi Huang, Guanzhi Deng +6
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.…
X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution
Fengyuan Liu, Yuchen Fu, Yuqi Wang +2
Human quantitative researchers mine alpha through an iterative process: they derive hypotheses from financial knowledge, implement and test them as factors, and use the resulting e…
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
Haochen Luo, Yi Huang, Sichun Luo +5
Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-…
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
Sichun Luo, Yi Huang, Haochen Luo +7
Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through execu…
ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models
Sichun Luo, Yi Huang, Mukai Li +5
Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or ambiguous informati…
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
Fengyuan Liu, Yi Huang, Sichun Luo +6
Discovering effective predictive signals, or "alphas," from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despit…