Xueqiao Sun, Xiao Liu, Bowen Lv, Hanchen Zhang, Bohao Jing, Zehan Qi, Yifan Xu, Yuxiao Dong, Jie Tang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models have opened up a world of possibilities for various NLP tasks, sparking optimism for the future.Despite their potential, LLMs have yet to be widely used as agents on real mobile devices.The main challenge is the need for high-quality data sources.Time constraints and labor intensity often hinder human annotation.On the other hand, existing LLMs exhibit inadequate completion rates and need a robust data filtration strategy.Given these challenges, we develop a framework called ANDROIDGEN to enhance the capabilities of LLM-based agents under data scarcity.In addition, we leverage AN-DROIDGEN to collect trajectories given human tasks and train open-source LLMs on these trajectories to develop an open-source mobile agent without manually labeled trajectories.We extensively evaluate ANDROIDGEN with AndroidWorld, AitW, and various popular applications, demonstrating its improvements and revealing potential areas for future improvement.Code, model, and data are available at https://github.com/THUDM/AndroidGen.

Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable \textbf{Visual Foundation Agents} that are postulated to excel across a myriad of tasks. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs as visual foundation agents in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and unified benchmark specifically designed to train and evaluate LMMs as visual foundation agents across diverse scenarios in one standard setting, including Embodied, Graphical User Interface, and Visual Design, with tasks formulated to probe the depth of LMMs' understanding and interaction capabilities. Through rigorous testing across 9 proprietary LMM APIs and 9 open models (18 in total), we demonstrate the considerable yet still developing visual agent capabilities of these models. Additionally, VAB explores the synthesizing of visual agent trajectory data through hybrid methods including Program-based Solvers, LMM Agent Bootstrapping, and Human Demonstrations, offering insights into obstacles, solutions, and trade-offs one may meet in developing open LMM agents. Our work not only aims to benchmark existing models but also provides an instrumental playground for future development into visual foundation agents. Code, train, and test data are available at \url{https://github.com/THUDM/VisualAgentBench}.

We present WebGLM, an enhanced Large Language Model (LLM)-based retrieval question-answering system based on the ChatGLM3-6B, offering significant improvements over previous systems. We aim to augment a pre-trained LLM with web search and reliable retrieval capabilities while being efficient for real-world deployments. Leveraging LLM’s in-context learning ability and a robust filter strategy, we create a high-quality training dataset and address the hallucination issue with a self-check mechanism. Our base model, ChatGLM3-6B, excels in extracting critical information and generating desired responses. We tackle the decline in retrieval effectiveness for complex queries with a keywording technique and incorporate more web content for references. We align with user preferences by training a human preference-aware scorer and employing DPO training for direct alignment. Extensive experiments, including human evaluations and the Turing test, demonstrate WebGLM’s superior performance against leading web-enhanced question-answering systems, significantly enhancing performance and efficiency. The code, demo, and data are at https://github.com/THUDM/WebGLM .

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Empowered by the large-scale pretrained language models, existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations. However, they are still plagued by the <b>hallucination</b> problem, causing unpredictable factual errors in the generated responses. Recently, knowledge-grounded dialogue generation models, that intentionally invoke external knowledge resources to more informative responses, are also proven to be effective in reducing hallucination. Following the idea of getting high-quality knowledge, a few efforts have achieved pretty good performance on this issue. As some inevitable knowledge noises may also lead to hallucinations, it is emergent to investigate the reason and future directions for building noise-tolerant methods in KGD tasks. In this paper, we analyze the causal story behind this problem with counterfactual reasoning methods. Based on the causal effect analysis, we propose a possible solution for alleviating the hallucination in KGD by exploiting the dialogue-knowledge interaction. Experimental results of our example implementation show that this method can reduce hallucination without disrupting other dialogue performance, while keeping adaptive to different generation models. We hope our efforts can support and call for more attention to developing lightweight techniques towards robust and trusty dialogue systems.

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively evaluate LLMs as agents on challenging tasks in interactive environments. We present AgentBench, a multi-dimensional benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities. Our extensive test over 29 API-based and open-sourced (OSS) LLMs shows that, while top commercial LLMs present a strong ability of acting as agents in complex environments, there is a significant disparity in performance between them and many OSS competitors that are no larger than 70B. We identify the typical reasons of failures in environments and LLMs, showing that poor long-term reasoning, decision-making, and instruction following abilities are the main obstacles for developing usable LLM agents. Improving instruction following and training on high quality multi-round alignment data could improve agent performance. And different from existing assumptions, training on code present ambivalent impacts on different agent tasks. Datasets, environments, and an integrated evaluation package for AgentBench are released at https://github.com/THUDM/AgentBench.

Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. Based on soccer game videos and synchronized commentary data, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). We experimentally test existing state-of-the-art (SOTA) methods on this resource to demonstrate the future directions for improvement in this challenging task. We hope that our data resource (now available at https://github.com/THU-KEG/goal) can serve researchers and developers interested in knowledge-grounded cross-modal applications.

We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM). Its goal is to augment a pre-trained large language model (LLM) with web search and retrieval capabilities while being efficient for real-world deployments. To achieve this, we develop WebGLM with strategies for the LLM-augmented retriever, bootstrapped generator, and human preference-aware scorer. Specifically, we identify and address the limitations of WebGPT (OpenAI), through which WebGLM is enabled with accuracy, efficiency, and cost-effectiveness advantages. In addition, we propose systematic criteria for evaluating web-enhanced QA systems. We conduct multi-dimensional human evaluation and quantitative ablation studies, which suggest the outperformance of the proposed WebGLM designs over existing systems. WebGLM with the 10-billion-parameter GLM (10B) is shown to perform better than the similar-sized WebGPT (13B) and even comparably to WebGPT (175B) in human evaluation. The code, demo, and data are at https://github.com/THUDM/WebGLM.

Large-scale pre-trained language models (PLMs) have shown promising advances on various downstream tasks, among which dialogue is one of the most concerned. However, there remain challenges for individual developers to create a knowledge-grounded dialogue system upon such big models because of the expensive cost of collecting the knowledge resources for supporting the system as well as tuning these large models for the task. To tackle these obstacles, we propose XDAI, a knowledge-grounded dialogue system that is equipped with the prompt-aware tuning-free PLM exploitation and supported by the ready-to-use open-domain external knowledge resources plus the easy-to-change domain-specific mechanism. With XDAI, the developers can leverage the PLMs without any fine-tuning cost to quickly create the open-domain dialogue systems as well as easily customize their own domain-specific systems. Extensive experiments including human evaluation, Turing test, and online evaluation have demonstrated the competitive performance of XDAI compared with the state-of-the-art general PLMs and specific PLMs for dialogue. XDAI pilots studies on the exploitation of PLMs and made intriguing findings which could be inspiring for the future research on other PLM-based applications.