arXiv AI
Joint Workflow and Prompt Optimization for User Behavior Simulation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 3
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
arXiv:2606. 02798v1 Announce Type: new Abstract: Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited.
arXiv Machine Learning
Oct 28
Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation
The paper introduces StressSim, an intent‑preserving adversarial user simulator designed to stress‑test multi‑turn agents by generating challenging yet valid user interactions. StressSim optimises high‑level adversarial plans for each task instance using a genetic prompt‑optimisation loop that leverages rollout traces, task‑completion signals, and validity feedback to reduce task success while keeping the user’s goal unchanged. Experiments on MultiWOZ, retail, and airline domains show that StressSim reveals significant robustness gaps in leading LLM agents—reducing tau‑bench pass^4 scores by up to 69%—while maintaining realistic conversation quality and goal preservation with a modest optimisation budget.
arXiv Machine Learning
Jun 30
Synthetic Interaction Data for Scalable Personalization in Large Language Models
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
arXiv AI
Jul 2
Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework
arXiv:2607. 00010v1 Announce Type: cross Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time.
arXiv AI
Sep 15
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
arXiv:2609.15066v1 Announce Type: cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcem...
arXiv Computation and Language
Oct 8
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
arXiv:2605.12894v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are uncle...