← Back to all news
arXiv Computation and Language By Xinglin Wang, Zishen Liu, Tong Zheng, Shaoxiong Feng, Peiwen Yuan, Yiwei Li, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Ji Zhang, Boyuan Pan, Kan Li

From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery

Read the original on arXiv Computation and Language →

The paper introduces PersonTTS, an amortized agentic policy-discovery framework for personalized test-time scaling (TTS) of large language models. PersonTTS aims to maximize the joint satisfaction of user-specified accuracy, latency, and inference-cost requirements by reusing prior search experience through requirement-matched controller initialization and source-distilled procedural guidance. Experiments on AIME and HMMT datasets demonstrate that PersonTTS outperforms strong TTS baselines in joint requirement satisfaction on unseen user profiles and reduces discovery-agent time and cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Aug 18

Budget-Aware Tool Use Enables Effective Agent Scaling

arXiv:2511. 17006v2 Announce Type: replace Abstract: Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool calls that directly constrain environmental interaction.

By Tengxiao Liu, Zifeng Wang, Jin Miao, I-Hung Hsu, Jun Yan, Jiefeng Chen, Rujun Han, Fangyuan Xu, Yanfei Chen, Ke Jiang, Samira Daruki, Yi Liang, William Yang Wang, Tomas Pfister, Chen-Yu Lee
llmsagents
More like this →
arXiv AI
Sep 10

Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models

The paper introduces ENOUGH, a method for creating minimal sufficient user profiles for personalized language models. ENOUGH iteratively adds behavioral records or stops, evaluating profile prefixes with a counterfactual search that balances downstream gains, user specificity, and token costs. The resulting profiles are distilled into a lightweight controller that orders records and triggers the generator only once, achieving better effectiveness and efficiency than existing baselines across six tasks.

By Minghang Liu, Qiang Qiu, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng
llmsrag
More like this →