IDRBench is a benchmark designed to evaluate the interactive capabilities of deep research agents that use large language models. It introduces controlled opportunities for clarification within a common workflow, comparing autonomous and interactive trajectories by measuring task‑specific report alignment and interaction cost. Experiments on 100 tasks with seven LLMs show that interaction consistently improves alignment, though its effectiveness varies depending on the agents’ questions and feedback integration.
By Yingchaojie Feng, Qiang Huang, Xiaoya Xie, Zhaorui Yang, Jun Yu, Wei Chen, Anthony K. H. Tung
arXiv:2607. 16610v1 Announce Type: new Abstract: Long-horizon AI agents are becoming increasingly capable, yet their interaction with users remains surprisingly thin.
By Chen Chen, Zhehuai Chen
arXiv:2609.08977v3 Announce Type: replace-cross
Abstract: In this work, we present Gander, a native multimodal duplex interaction model that builds on MiniCPM-o 4.5 and is further adapted for realtim...
By Orantqing, Shengpeng Ji, Junlong Tong, Jialong Zuo, Dongjie Fu, Di Cao, Yangzhuo Li, Shangda Wu, Franz, Evan, Theron Veyra, Changhao Pan, Jingyu Lu, Dongchao Yang, Zhifei Xie, Yang Tan, Xiaoyu Shen, Xiaoda Yang, Wenfu Wang, Teddy Sun, Steve Yves, Zhou Zhao
arXiv:2509.08494v2 Announce Type: replace-cross
Abstract: As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures....
By Benjamin Sturgeon, Daniel Samuelson, Jacob Haimes, Jacy Reese Anthis
arXiv:2609.22249v1 Announce Type: new
Abstract: This paper treats prompt engineering as a discipline for turning informal human intent into structured AI work specifications. It develops the practice...
By Erfan Loweimi, Hadi Daneshvar, Samira Loveymi, Samir Ouelha, Zhengjun Yue, Hajar Mozaffar, Saturnino Luz
arXiv:2608. 07494v1 Announce Type: cross Abstract: AI tools like ChatGPT and DeepSeek, powered by Large Language Models (LLMs), allow users to obtain instant and effective content responses simply by typing requests, such as ``plan a three-day Vienna trip'', ``solve the attached mathematical problem'', ``draft an email to inquire review progress'', etc.
By Yiqun Zhang, Yunfan Zhang, Mingjie Zhao, Sen Feng, Yiu-ming Cheung
EduDial is a large-scale multi-turn teacher‑student dialogue corpus covering 345 core knowledge points and 34,250 dialogue sessions, designed around Bloom’s taxonomy and ten questioning strategies such as situational, ZPD, and metacognitive questioning. The dataset includes differentiated teaching strategies for students at varying cognitive levels to provide targeted guidance. Using EduDial, the authors trained EduDial‑LLM 32B and introduced an 11‑dimensional evaluation framework that measures teaching quality and content quality, showing that most mainstream LLMs struggle with student‑centered teaching while EduDial‑LLM outperforms all baselines across all metrics.
By Shouang Wei, Min Zhang, Xin Lin, Bo Jiang, Zhongxiang Dai, Kun Kuang
arXiv:2607. 17191v1 Announce Type: new Abstract: Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc.
By Wentao Liu, Siyu Song, Xi Chen, Youjia Li, Xiaokun Wang, Min Ji, Ji Wang
arXiv:2607. 14109v1 Announce Type: cross Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding.
By Inder Preet, Shuxin Lin, Dhaval Patel
The paper proposes PAIR, a method that treats reasoning paths of large language models as phase‑structured trajectories within each question. By sampling multiple trajectories per question, aligning them to shared relative phases, and comparing successful versus unsuccessful paths only within the same phase, PAIR isolates path‑quality signals from question‑level variation. Experiments show that standard correctness probes lose predictive power under this within‑question evaluation, while PAIR improves trajectory ranking, Best‑of‑N selection, and enables phase‑wise steering of generation outcomes.
By Zhenghao He, Guangzhi Xiong, Sanchit Sinha, Bohan Liu, Wenqian Ye, Aidong Zhang
The article surveys multi‑turn conversational AI, highlighting its shift from isolated text prompts to sustained, multimodal interactions that involve clarifying goals, revising requests, and switching topics. It reviews literature across text‑only dialogue, AudioLLMs, multimodal and omni‑modal systems, and tool‑augmented agents, organizing findings around datasets, models, training, evaluation, and cross‑cutting challenges. The analysis reveals that while multimodal perception and action have progressed rapidly, systems still struggle with persistent memory, cross‑turn grounding, full‑duplex interaction, robust evaluation, and cultural alignment.
By Syeda Faiza Ahmed, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury
Hy‑MultiTurn is a Chinese benchmark designed to evaluate deep multi‑turn dialogue understanding over long interactions. It introduces six controlled evaluation modes—constraint memory, precise execution, constraint synthesis, object localization, action suppression, and reference resolution—across 209 tasks ranging from 12 to 76 turns, incorporating dialogue length, irrelevant distractions, and colloquial phrasing. Testing 22 state‑of‑the‑art models shows the benchmark is highly challenging, with even the best model meeting all criteria only 41.1% of the time and no model excelling in every mode.
By Eileen Ye, Jiawen Tao, Yaoming Li, Chenxu Liu, Wenhan Yu, Yaxin Fan, Xiaokun Yuan, Mengzhou Wu, Yanbing Jiang, Maxm Pan