SimXAI is a lightweight, LLM‑centric conversational layer that replaces traditional intent recognition, dialogue management, and template‑based response modules in GUS‑style ConvXAI agents. By using a single tool‑calling LLM to interface with existing XAI resources, it provides a modular interface that improves function‑selection accuracy, faithfulness, and handling of context‑dependent requests. In a user study, substituting SimXAI for the conversational layer of the TalkToModel agent led to more accurate task completion in fewer turns, demonstrating enhanced conversational quality while preserving faithfulness.
By Van Bach Nguyen, Qianli Wang, Nils Feldhus, J\"org Schl\"otterer, Christin Seifert
The paper proposes ‘meta access’—a structured, permissioned view of an interface’s state—to enhance large language model chat UIs. It outlines a ladder of access levels, from feature tutoring to full orchestration, and demonstrates the concept with the Meta Chat prototype, which uses summaries, settings, and message links to enable reversible changes and a browsable tutorial library. Meta access aims to transform chat from a single conversation window into a control layer for the entire workspace while addressing risks such as grounding, privacy, and prompt injection.
By Julian Kunkel, Ali Doosthosseini
arXiv:2604.23069v2 Announce Type: replace
Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may dro...
By Yating Wu, Yuhao Zhang, Sayan Ghosh, Sourya Basu, Anoop Deoras, Jun Huan, Gaurav Gupta
Agent Seer is a pipeline that automatically synthesizes realistic evaluation scenarios for AI agents that use external tools, using only the tool’s specification (function names, natural‑language descriptions, and typed parameter schemas). Starting from a single Model Context Protocol (MCP) specification, it enriches raw schemas, generates graded scenarios with synthetic tool outputs, and expands them into mock‑data‑grounded multi‑turn dialogues that demonstrate strong tool‑calling correctness and conversational coherence. Across seven diverse MCP specifications, the pipeline achieves high quality, with parameter‑schema complexity emerging as the main driver of quality variation and argument‑value accuracy identified as the dominant failure mode.
By Harish Karumuri, Mahesh Vemula, David Lopes Pegna
arXiv:2610.15765v1 Announce Type: cross
Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were design...
By Alan Wu, Wei Tao, Yiwen Guo
arXiv:2606. 09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools.
By Wanli Li, Bowen Zhou, Yunyao Yu, Zhou Xu, Yifan Yang, Dongsheng Li, Caihua Shan
arXiv:2609.37743v1 Announce Type: new
Abstract: LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even...
By Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang, Jason Mars
arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.
By Niranjan Kumar M, Balaji Nagarajan, Karthik Nair, Faysal Satter, Nithin Surendran
ChatDev 2.0, also called DevAll, is a no-code platform that lets users build, run, and inspect heterogeneous multi‑agent systems (MAS) powered by large language models. It combines a declarative executable graph abstraction with a cycle‑aware execution engine, enabling representation and execution of dynamic, cyclic interactions among diverse agents. The integrated visual interface allows users to author, monitor, and inspect MAS—including human‑in‑the‑loop steps—without writing code, and experiments show it matches state‑of‑the‑art MAS performance across three tasks.
By Yufan Dang, Shu Yao, Bowen Lai, Chenting Xu, Ruijie Shi, Wai-Shing Leung, Huatao Li, Chen Qian, Zhiyuan Liu
arXiv:2601. 04203v2 Announce Type: replace-cross Abstract: We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback.
By Xueqing Wu, Zihan Xue, Da Yin, Shuyan Zhou, Kai-Wei Chang, Nanyun Peng, Yeming Wen
arXiv:2609.08318v1 Announce Type: cross
Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE task...
By Zhengran Zeng, Yixin Li, Rui Xie, Wei Ye, Shikun Zhang
The paper introduces a method for efficient agent evaluation by using cached traces from task executions. It proposes summarizing each trace with an LLM and embedding the summary to capture task-relevant signals while reducing system-identifying noise. Using these representations, the authors build low-dimensional system embeddings and predict a new system’s benchmark score, achieving lower error than baseline models on SWE-bench Verified and Terminal-Bench 2.0 with only a single executed task.
By Ben Johnson, Hayden Helm