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.

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing the text generation quality in a wide range of tasks. However, there still remains a reliability gap between LLM-as-a-Judge and human evaluation. One important reason is the lack of guided oracles in the evaluation process. Motivated by the role of reference pervasively used in classic text evaluation, we introduce RevisEval, a novel text generation evaluation paradigm via the response-adapted references. RevisEval is driven by the key observation that an ideal reference should maintain the necessary relevance to the response to be evaluated. Specifically, RevisEval leverages the text revision capabilities of large language models (LLMs) to adaptively revise the response, then treat the revised text as the reference (response-adapted reference) for the subsequent evaluation. Extensive experiments demonstrate that RevisEval outperforms traditional reference-free and reference-based evaluation paradigms that use LLM-as-a-Judge across NLG tasks and open-ended instruction-following tasks. More importantly, our response-adapted references can further boost the classical text metrics, e.g., BLEU and BERTScore, compared to traditional references and even rival the LLM-as-a-Judge. A detailed analysis is also conducted to confirm RevisEval's effectiveness in bias reduction, the impact of inference cost, and reference relevance.

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation

LLM agents enhanced by tree search algorithms have yielded notable performances in code generation. However, current search algorithms in this domain suffer from low search quality due to several reasons: 1) Ineffective design of the search space for the high-reasoning demands of code generation tasks, 2) Inadequate integration of code feedback with the search algorithm, and 3) Poor handling of negative feedback during the search, leading to reduced search efficiency and quality. To address these challenges, we propose to search for the reasoning process of the code and use the detailed feedback of code execution to refine erroneous thoughts during the search. In this paper, we introduce RethinkMCTS, which employs the Monte Carlo Tree Search (MCTS) algorithm to conduct thought-level searches before generating code, thereby exploring a wider range of strategies. More importantly, we construct verbal feedback from fine-grained code execution feedback to refine erroneous thoughts during the search. This ensures that the search progresses along the correct reasoning paths, thus improving the overall search quality of the tree by leveraging execution feedback. Through extensive experiments, we demonstrate that RethinkMCTS outperforms previous search-based and feedback-based code generation baselines. On the HumanEval dataset, it improves the pass@1 of GPT-3.5-turbo from 70.12 to 89.02 and GPT-4o-mini from 87.20 to 94.51. It effectively conducts more thorough exploration through thought-level searches and enhances the search quality of the entire tree by incorporating rethink operation.

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.

Performance Law of Large Language Models

Guided by the belief of the scaling law, large language models (LLMs) have achieved impressive performance in recent years. However, scaling law only gives a qualitative estimation of loss, which is influenced by various factors such as model architectures, data distributions, tokenizers, and computation precision. Thus, estimating the real performance of LLMs with different training settings rather than loss may be quite useful in practical development. In this article, we present an empirical equation named "Performance Law" to directly predict the MMLU score of an LLM, which is a widely used metric to indicate the general capability of LLMs in real-world conversations and applications. Based on only a few key hyperparameters of the LLM architecture and the size of training data, we obtain a quite accurate MMLU prediction of various LLMs with diverse sizes and architectures developed by different organizations in different years. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.

AIE: Auction Information Enhanced Framework for CTR Prediction in Online Advertising

Click-Through Rate (CTR) prediction is a fundamental technique for online advertising recommendation and the complex online competitive auction process also brings many difficulties to CTR optimization. Recent studies have shown that introducing posterior auction information contributes to the performance of CTR prediction. However, existing work doesn't fully capitalize on the benefits of auction information and overlooks the data bias brought by the auction, leading to biased and suboptimal results. To address these limitations, we propose Auction Information Enhanced Framework (AIE) for CTR prediction in online advertising, which delves into the problem of insufficient utilization of auction signals and first reveals the auction bias. Specifically, AIE introduces two pluggable modules, namely Adaptive Market-price Auxiliary Module (AM2) and Bid Calibration Module (BCM), which work collaboratively to excavate the posterior auction signals better and enhance the performance of CTR prediction. Furthermore, the two proposed modules are lightweight, model-agnostic, and friendly to inference latency. Extensive experiments are conducted on a public dataset and an industrial dataset to demonstrate the effectiveness and compatibility of AIE. Besides, a one-month online A/B test in a large-scale advertising platform shows that AIE improves the base model by 5.76% and 2.44% in terms of eCPM and CTR, respectively.

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the winning response and the losing response within pairwise data are generated isolatedly, leading to weak correlations between them as well as suboptimal alignment performance. To address this issue, we propose an effective framework named BMC, for bridging and modeling correlations in pairwise data. Firstly, we increase the consistency and informativeness of the pairwise preference signals by targeted modifications, synthesizing a pseudo winning response through improving the losing response based on the winning response. Secondly, we identify that DPO alone is insufficient to model these correlations and capture nuanced variations. Therefore, we propose learning token-level correlations by dynamically leveraging the policy model's confidence during training. Comprehensive experiments on QA, math, and instruction-following tasks demonstrate the effectiveness of our approach, significantly surpassing competitive baselines, including DPO. Additionally, our in-depth quantitative analysis reveals the reasons behind our method's superior performance over DPO and showcases its versatility to other DPO variants.

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.