Signals 4 · free daily AI digest

PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems

Paper recorded by Signals 4 on 2026-08-28 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.CL · 自然语言处理 · first seen 2026-08-31

Abstract

Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. Our analysis of 16K real-world sessions shows that 75.9% of interactions are multi-turn, revealing a substantial gap between how users interact with agents and how such systems are trained and evaluated. We introduce \tex

Read on arXiv →

#185 most recent of 186 cs.CL papers we have recorded · ↑ newer: When Linguistic and Internal Confidence Diverge in Large Language Mode · ↓ older: BanglaMed-QA: A Question Answering System for Healthcare Support in Ba
Cite this page: PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems: the #185 most recent of 186 cs.CL papers we have recorded (as of 2026-08-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/personaforge-realistic-multi-turn-user-simulation-for-agentic-systems.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions