Newest papers

Towards User Simulators That Stay On Task And Still Sound Natural

Mustafa Omer Gul, Philippe Laban, Tanya Goyal, Jennifer Neville · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31512 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

ユーザーはますますAIシステムに依存し、拡張された複数のターンタスクを行うが、証拠は、LLMベースのシステムパフォーマンスが長期的な相互作用に比べて劣化していることを示しています。 AIアシスタントを評価し、そのような設定で改善するには、複雑なユーザーの意図に忠実に従うユーザーシミュレータが必要です。現存するアプローチは、共にタスクの意図の遵守と行動の自然性を報酬する強化学習(RL)レシピを提案します:推奨されたアシスタントは、複雑なユーザーの意図に従うことができますが、行動の忠誠さが欠けますが、専門のユーザーシミュレータは、シミュレータと対立する、対立的なループで訓練された軽量

Machine translation (Meta M2M100); the English original follows.

Abstract

Users increasingly rely on AI systems for extended, multi-turn tasks, yet evidence indicates that LLM-based system performance degrades over prolonged interaction. To evaluate and improve AI assistants in such settings, we need user simulators that faithfully follow complex user intents while exhibiting realistic conversational behavior. Existing approaches manifest a trade-off: prompted assistants can follow complex user intents but lack behavioral fidelity, while specialized user simulators better approximate conversational behavior but struggle to remain faithful to complex intents. In this paper, we propose a reinforcement learning (RL) recipe that jointly rewards task intent adherence and behavioral naturalness. A crucial contribution of the method is operationalizing naturalness with a lightweight discriminator trained in an alternating, adversarial loop with the user simulator. We release the resulting model, UserLM-2.0, which produces valid simulated conversations (i.e., meeting both task-faithfulness and naturalness criteria) 46.2% of the time, over three times the rate of the strongest prior user simulator (14.1%).

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Naturalness, Computer science, Human–computer interaction, Task (project management), Operationalization, User modeling

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange