arXiv Machine Learning August 7, 2026 By Guanyu Wang, Zidi Zhang, Xu Chu

FOCUS: Decoupling Expert Personas in LLMs to Enhance Domain Expert Capabilities

Read the original on arXiv Machine Learning →

arXiv:2608. 05611v1 Announce Type: cross Abstract: Large Language Models (LLMs) can exhibit diverse personas, and activating expert personas has been shown to improve domain expertise and task accuracy.

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 Machine Learning.

arXiv AI

Aug 14

Synthetic Persona Pretraining: Alignment from Token Zero

arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.

By Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, Roland Aydin, Robert West

agents safety

arXiv Computation and Language

3d ago

LLM Persona Unlearning

arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-...

By Kemou Li, Zhuan Shi, Qizhou Wang, Fengpeng Li, Negar Rostamzadeh, Golnoosh Farnadi, Jiantao Zhou

llms benchmarks

arXiv Machine Learning

Jun 24

Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control

arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.

By Harshvardhan Saini, Yiming Tang, Dianbo Liu

llms safety

arXiv Machine Learning

Sep 3

DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation

The paper introduces Document-Mediated Reinforcement Learning (DMRL), a framework that treats skill document optimization in advertising recommendation as a sequence of structured editing actions. An upper-level agent edits the skill documents while a frozen lower-level task agent evaluates the edits via A/B testing. DMRL incorporates Dual-Relative Policy Optimization for robust advantage estimation and a Long-term Reward Predictor that models population heterogeneity to estimate long-term outcomes, achieving superior performance on a large-scale short‑video ads platform.

By Wei Zhang, Hongji Li, Song Sun, Peng Yu, Xue Yang, Lei Zhao, Peng Jiang

llms agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Aug 30

R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment

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 Persona Selection--Realiz...

benchmarks safety

arXiv AI

Aug 7

Role Steering of Language Models for Social Simulations

arXiv:2608. 00023v2 Announce Type: replace-cross Abstract: Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population.

By Isaac Song, Mohammed Rehan Parwani, Glenn Matlin, Emile Anand, Akhil Theerthala, Arjun Chatterjee, Anthony Wen-Ming Zang, Maria Kostylew, Yonadav G. Shavit, Sebastien Krier, Mark Riedl

llms agents safety