TY - GEN
T1 - Adaptive Preference Arithmetic
T2 - 39th Conference on Neural Information Processing Systems, NeurIPS 2025
AU - Nie, Hongyi
AU - Wang, Yaqing
AU - Zhou, Mingyang
AU - Pan, Feiyang
AU - Yao, Quanming
AU - Wang, Zhen
N1 - Publisher Copyright:
© 2025 Neural information processing systems foundation. All rights reserved.
PY - 2025
Y1 - 2025
N2 - As large language models (LLMs) are increasingly used as personalized user assistants, effectively adapting to users' evolving preferences is critical for delivering high-quality personalized responses. While user preferences are often stable in content, their relative strengths shift over time due to changing goals and contexts. Therefore, modeling these dynamic preference strengths can enable finer-grained personalization. However, current methods face two major challenges: (i) limited user feedback makes it difficult to estimate preference strengths accurately, and (ii) natural language ambiguity limits the controllability of preference-guided generation. To address these issues, we propose AdaPA-Agent, a LLM-agent personalization framework that models dynamic preference strengths via Adaptive Preference Arithmetic. First, instead of requiring additional user feedback, AdaPA-Agent employs an alignment-based strength estimation module to estimate the strength of user preferences from the existing user-agent interaction. Then, it guides controllable personalized generation by linearly combining next-token distributions, weighted by the estimated strengths of individual preferences. Experiments on two personalization tasks-conversational recommendation and personalized web interaction-demonstrate that AdaPA-Agent better aligning with users' changing intents, and has achieved over 18.9% and 14.2% improvements compared to ReAct, the widely-used agent framework.
AB - As large language models (LLMs) are increasingly used as personalized user assistants, effectively adapting to users' evolving preferences is critical for delivering high-quality personalized responses. While user preferences are often stable in content, their relative strengths shift over time due to changing goals and contexts. Therefore, modeling these dynamic preference strengths can enable finer-grained personalization. However, current methods face two major challenges: (i) limited user feedback makes it difficult to estimate preference strengths accurately, and (ii) natural language ambiguity limits the controllability of preference-guided generation. To address these issues, we propose AdaPA-Agent, a LLM-agent personalization framework that models dynamic preference strengths via Adaptive Preference Arithmetic. First, instead of requiring additional user feedback, AdaPA-Agent employs an alignment-based strength estimation module to estimate the strength of user preferences from the existing user-agent interaction. Then, it guides controllable personalized generation by linearly combining next-token distributions, weighted by the estimated strengths of individual preferences. Experiments on two personalization tasks-conversational recommendation and personalized web interaction-demonstrate that AdaPA-Agent better aligning with users' changing intents, and has achieved over 18.9% and 14.2% improvements compared to ReAct, the widely-used agent framework.
UR - https://www.scopus.com/pages/publications/105048513307
M3 - 会议稿件
AN - SCOPUS:105048513307
T3 - Advances in Neural Information Processing Systems
SP - 115166
EP - 115191
BT - 39th Conference on Neural Information Processing Systems, NeurIPS 2025
PB - Neural information processing systems foundation
Y2 - 2 December 2025 through 7 December 2025
ER -