arXiv:2607. 12180v1 Announce Type: cross Abstract: An AI teammate's design properties (personality, communication style, when it speaks) can shape a team's trust, coordination, and decisions.
The paper introduces the Human‑AI Interaction Description Language (HAIDL), a formal model that treats human‑AI interactions as durable data objects rather than fleeting prompt‑response exchanges. HAIDL captures detailed context—including computational environment, user requests, prompts, AI responses, feedback, provenance, and model metadata—using a Backus‑Naur Form‑inspired syntax. The authors implement HAIDL in HAIDL‑X, a JupyterLab middleware that records interactions, builds contextual prompts, interfaces with AI providers, and stores data for replay, analysis, and learning about user behavior.
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.
The paper introduces the Core Sentiment Inventory (CSI), a new personality trait evaluation tool for large language models (LLMs) that addresses reliability and validity issues found in existing methods like the Big Five Inventory (BFI). CSI is designed specifically for LLMs, supports both English and Chinese, and provides detailed psychological portraits of model behavior. Experiments show that CSI captures nuanced behavioral patterns, improves reliability, and correlates strongly (above 0.85) with real-world LLM outputs.
Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs).
arXiv:2609.07594v1 Announce Type: cross Abstract: Conversational Task Assistants (CTAs) are multimodal dialogue systems that support users in complex real-world tasks such as cooking and DIY through...
Kolab is a new dataset comprising over 115 hours of screen recordings from 50 professionals across 40 occupations who collaborate with AI agents on realistic, long‑horizon tasks. The dataset includes participants’ judgments of collaboration quality and output, revealing varied coordination patterns and the need for agents to anticipate how experts will use or modify their contributions. Analysis shows current state‑of‑the‑art models overestimate collaboration success and struggle to differentiate high‑ from low‑quality interactions, indicating a gap in understanding long‑horizon human‑agent teamwork.
PIVOTSBench is a benchmark designed to assess multimodal large language models’ ability to reason about fine‑grained interpersonal relationships. It is constructed from Social‑IQ 2.0 and YouTube data and evaluates models on predicting bidirectional relationship dimensions grounded in psychology research. The benchmark also includes auxiliary tasks that test models’ capacity to identify and use critical visual cues, and it examines the impact of visual modalities, social role information, and different prediction settings on model performance.
The paper introduces A-B-D, a method that infers personality traits of large language model agents from their behavioral data, combining functional actions and linguistic outputs across 345,667 real-world trajectories of 80 models. After filtering for stability and discriminability, 79 features are reduced to six reliable factors—two functional and four linguistic—revealing differences such as Claude‑Sonnet‑4.6’s planfulness versus GPT‑5.5’s low energy. The study also demonstrates a weak correlation between these inferred traits and agents’ self-reported Big Five scores, highlighting a knowledge‑action gap.
The paper introduces UC-Bench, a human‑annotated benchmark for detecting user‑side implicit conflicts in Human‑LLM dialogue, a problem largely overlooked compared to LLM‑side conflicts. Experiments show current LLMs struggle with these conflicts, especially when they stem from implicit incompatibilities in dialogue history. To address this, the authors propose SynUC, a constraint‑guided data synthesis method that generates a new training set, UC‑Data, which improves performance of lightweight LLMs on UC‑Bench compared to larger general‑purpose models and existing synthesis approaches.
arXiv:2610.34889v1 Announce Type: new Abstract: Controlling personality in large language models is important for building conversational agents that can be customized to different users and interact...
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.