GUI Agents with Foundation Models: A Comprehensive Survey

Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), facilitate intelligent agents being capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions by simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data, frameworks, and applications. We begin by discussing representative datasets and benchmarks. Next, we summarize a unified framework that captures the essential components used in prior research, accompanied by a taxonomy. Additionally, we explore commercial applications of (M)LLM-based GUI agents. Drawing from existing work, we identify several key challenges and propose future research directions. We hope this paper will inspire further developments in the field of (M)LLM-based GUI agents.

Beyond Positive History: Re-ranking with List-level Hybrid Feedback

As the last stage of recommender systems, re-ranking generates a re-ordered list that aligns with the user's preference. However, previous works generally focus on item-level positive feedback as history (e.g., only clicked items) and ignore that users provide positive or negative feedback on items in the entire list. This list-level hybrid feedback can reveal users' holistic preferences and reflect users' comparison behavior patterns manifesting within a list. Such patterns could predict user behaviors on candidate lists, thus aiding better re-ranking. Despite appealing benefits, extracting and integrating preferences and behavior patterns from list-level hybrid feedback into re-ranking multiple items remains challenging. To this end, we propose Re-ranking with List-level Hybrid Feedback (dubbed RELIFE). It captures user's preferences and behavior patterns with three modules: a Disentangled Interest Miner to disentangle the user's preferences into interests and disinterests, a Sequential Preference Mixer to learn users' entangled preferences considering the context of feedback, and a Comparison-aware Pattern Extractor to capture user's behavior patterns within each list. Moreover, for better integration of patterns, contrastive learning is adopted to align the behavior patterns of candidate and historical lists. Extensive experiments show that RELIFE significantly outperforms SOTA re-ranking baselines.

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set of tools, formulating a requirement based on these tools, and generating the call statements. However, tools sampled randomly lack relevance, making them difficult to combine and thus reducing the diversity of the data. Additionally, current work overlooks the coherence between turns of dialogues, leading to a gap between the synthesized data and real-world scenarios. To address these issues, we propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues. We integrate these two strategies and enable multiple agents to synthesize the dialogue data interactively, resulting in our tool-calling data synthesis pipeline ToolFlow. Data quality assessments demonstrate improvements in the naturalness and coherence of our synthesized dialogues. Finally, we apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow. Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities.

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications.

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either accepted or rejected. The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents. Building on this, we develop a comprehensive data generation pipeline to create a diverse dataset, ProactiveBench, containing 6,790 events. Finally, we demonstrate that fine-tuning models with the proposed ProactiveBench can significantly elicit the proactiveness of LLM agents. Experimental results show that our fine-tuned model achieves an F1-Score of 66.47% in proactively offering assistance, outperforming all open-source and close-source models. These results highlight the potential of our method in creating more proactive and effective agent systems, paving the way for future advancements in human-agent collaboration.

ToolACE: Winning the Points of LLM Function Calling

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models

Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge. Recently, large language models (LLMs) have shown promise in bridging this gap. However, previous attempts to directly implement LLMs as recommenders fall short in meeting the requirements of industrial RSs, particularly in terms of online inference latency and offline resource efficiency. Thus, we propose REKI to acquire two types of external knowledge about users and items from LLMs. Specifically, we introduce factorization prompting to elicit accurate knowledge reasoning on user preferences and items. We develop individual knowledge extraction and collective knowledge extraction tailored for different scales of scenarios, effectively reducing offline resource consumption. Subsequently, generated knowledge undergoes efficient transformation and condensation into augmented vectors through a hybridized expert-integrated network, ensuring compatibility. The obtained vectors can then be used to enhance any conventional recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from LLMs. Experiments demonstrate that REKI outperforms state-of-the-art baselines and is compatible with lots of recommendation algorithms and tasks. Now, REKI has been deployed to Huawei's news and music recommendation platforms and gained a 7% and 1.99% improvement during the online A/B test.

Prompt Tuning as User Inherent Profile Inference Machine

Large Language Models (LLMs) have exhibited significant promise in recommender systems by empowering user profiles with their extensive world knowledge and superior reasoning capabilities. However, LLMs face challenges like unstable instruction compliance, modality gaps, and high inference latency, leading to textual noise and limiting their effectiveness in recommender systems. To address these challenges, we propose UserIP-Tuning, which uses prompt-tuning to infer user profiles. It integrates the causal relationship between user profiles and behavior sequences into LLMs' prompts. And employs expectation maximization to infer the embedded latent profile, minimizing textual noise by fixing the prompt template. Furthermore, A profile quantization codebook bridges the modality gap by categorizing profile embeddings into collaborative IDs, which are pre-stored for online deployment. This improves time efficiency and reduces memory usage. Experiments on four public datasets show that UserIP-Tuning outperforms state-of-the-art recommendation algorithms. Additional tests and case studies confirm its effectiveness, robustness, and transferability.

A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems

Recently, increasing attention has been paid to LLM-based recommender systems, but their deployment is still under exploration in the industry. Most deployments utilize LLMs as feature enhancers, generating augmentation knowledge in the offline stage. However, in recommendation scenarios, involving numerous users and items, even offline generation with LLMs consumes considerable time and resources. This generation inefficiency stems from the autoregressive nature of LLMs, and a promising direction for acceleration is speculative decoding, a Draft-then-Verify paradigm that increases the number of generated tokens per decoding step. In this paper, we first identify that recommendation knowledge generation is suitable for retrieval-based speculative decoding. Then, we discern two characteristics: (1) extensive items and users in RSs bring retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for text generated by LLMs. Based on the above insights, we propose a Decoding Acceleration Framework for LLM-based Recommendation (dubbed DARE), with Customized Retrieval Pool to improve retrieval efficiency and Relaxed Verification to increase the acceptance rate of draft tokens, respectively. Extensive experiments demonstrate that DARE achieves a 3-5x speedup and is compatible with various frameworks and backbone LLMs. DARE has also been deployed to online advertising scenarios within a large-scale commercial environment, achieving a 3.45x speedup while maintaining the downstream performance.

All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era

Recommender systems (RS) are vital for managing information overload and delivering personalized content, responding to users' diverse information needs. The emergence of large language models (LLMs) offers a new horizon for redefining recommender systems with vast general knowledge and reasoning capabilities. Standing across this LLM era, we aim to integrate recommender systems into a broader picture, and pave the way for more comprehensive solutions for future research. Therefore, we first offer a comprehensive overview of the technical progression of recommender systems, particularly focusing on language foundation models and their applications in recommendation. We identify two evolution paths of modern recommender systems -- via list-wise recommendation and conversational recommendation. These two paths finally converge at LLM agents with superior capabilities of long-term memory, reflection, and tool intelligence. Along these two paths, we point out that the information effectiveness of the recommendation is increased, while the user's acquisition cost is decreased. Technical features, research methodologies, and inherent challenges for each milestone along the path are carefully investigated -- from traditional list-wise recommendation to LLM-enhanced recommendation to recommendation with LLM agents. Finally, we highlight several unresolved challenges crucial for the development of future personalization technologies and interfaces and discuss the future prospects.