6 papers · 1 filter
RA: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment
Mohan Zhang, Chengsong You, Xiaoyu Cao +4
The same Persona behavior can be beneficial in one context but harmful in another, causing static Persona elicitation to perform inconsistently across tasks. We introduce the Perso…
TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
Yongchao Chen, Jiefeng Chen, Rui Meng +6
While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guid…
CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
Yongchao Chen, Yilun Hao, Yueying Liu +2
Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We int…
Steering Large Language Models between Code Execution and Textual Reasoning
Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma +2
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains,…
PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling
Yongchao Chen, Jacob Arkin, Yilun Hao +3
Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for s…
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
Yongchao Chen, Rujul Gandhi, Yang Zhang +1
Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) a…