UXBench is the first user‑centric benchmark that uses real user feedback to evaluate AI assistants. It comprises three tasks—UX Judge, UX Eval, and UX Recovery—built from 7,400 test instances drawn from over 70,000 interaction logs of a mainstream Chinese AI assistant, covering 8 scenarios and 83 domains. Experiments on 26 state‑of‑the‑art language models reveal how model capability affects user experience and highlight six key findings about user feedback prediction and engagement.
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
UXBench Pro is a new benchmark that evaluates personalized user experience in multi-turn dialogue interactions. It contains 1,000 test instances from real user interactions across 12 task scenarios and 82 domains, each paired with a FACTORS user profile describing seven behavioral facets. The benchmark introduces a dual-perspective evaluation: a personalized User Reward Model for third‑person judgment and Sim4Eval, a user simulator for first‑person evaluation across four cognitive state dimensions, along with meta‑benchmarks URMBench and USimBench to assess evaluator reliability.
arXiv:2608.02372v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used to support decisions by calling external tools. Existing work on LLM tool-calling assumes t...
arXiv:2607. 20485v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations.
arXiv:2610.09163v1 Announce Type: new Abstract: Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when...
arXiv:2607. 20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services.
arXiv:2606. 05697v1 Announce Type: new Abstract: User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly.
arXiv:2605. 28882v2 Announce Type: replace-cross Abstract: With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important.
User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly. In light of this, recent work has explored Multimodal Large Language Models as proxy evaluators.
The paper introduces Test-Time Adaptation through Human‑Agent Interaction (TAHI), a method that uses iterative human feedback to adapt AI agents to individual users’ criteria. By integrating cross‑session interaction data into agent context and weights, and building an evolving rubric module, the authors demonstrate that agents can improve task success by 4.5–20.9% after only a few interactions. The evolving rubric also serves as a scalable annotation tool, detecting 16.0–22.3% more failures than language models or humans alone, and personalized agents can even generalize improvements up to 8.8% across users.
WorldBench is a new multilingual benchmark that tests large language model agents on culturally grounded everyday workflows, offering 1,600 tasks in seven languages and eight cultures. The benchmark evaluates agents through structured sandbox actions and introduces Constrained Task Success (CTS), a metric that assesses task completion, minimal modification, and other complementary aspects via deterministic and LLM-as-a-Judge evaluations. Experiments show that even leading models achieve only 49.2% CTS, revealing significant gaps in correctness and state preservation across languages and cultures.
The paper introduces user simulators that provide intrinsic feedback by incorporating latent evaluation states such as internal thoughts, reactions, and scalar ratings. These simulators, trained on real user–assistant interaction logs, outperform prompted baselines in realism and critiquing behaviors, and their turn‑level evaluations better align with human judgments. Additionally, the intrinsic feedback serves as an effective reward signal for multi‑turn reinforcement learning, reducing compute requirements by over 50% compared to setups using external judge LLMs.