Seq2Seq AP - 44.8 (e) Large vocabulary object detection.

In recent years, the remarkable progress of large language models (LLMs) has sparked interest in task automation, which involves decomposing complex tasks described by user instructions into sub-tasks and invoking external tools to execute them, playing a central role in autonomous agents. However, there is a lack of systematic and standardized benchmarks to promote the development of LLMs in task automation. To address this, we introduce TaskBench, a comprehensive framework to evaluate the capability of LLMs in task automation. Specifically, task automation can be divided into three critical stages: task decomposition, tool selection, and parameter prediction. To tackle the complexities inherent in these stages, we introduce the concept of Tool Graph to represent decomposed tasks and adopt a back-instruct method to generate high-quality user instructions.

Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as applying vouchers, managing budgets, and finding multi-products seller. To bridge this gap, we propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent. Specifically, we propose a scalable framework to simulate user instructions based on various intents derived from sampled real-world products. To facilitate consistent and reliable evaluations, we provide a large-scale shopping sandbox that serves as an interactive simulated environment, incorporating over 2.5 million real-world products. Experimental results demonstrate that even state-of-the-art language agents (such as GPT-4.1) achieve absolute success rates under 50% on our benchmark tasks, highlighting the significant challenges posed by our ShoppingBench. In addition, we propose a trajectory distillation strategy and leverage supervised fine-tuning, along with reinforcement learning on synthetic trajectories, to distill the capabilities of a large language agent into a smaller one. As a result, our trained agent achieves competitive performance compared to GPT-4.1.

To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following in the real world poses significant challenges beyond performing a single, clearly defined task. For instance, real-world human instructions can be ambiguous, require different levels of AI assistance, and may evolve over time, reflecting changes in the user's mental state. To address this gap, we introduce RealWebAssist, a novel benchmark designed to evaluate sequential instruction-following in realistic scenarios involving long-horizon interactions with the web, visual GUI grounding, and understanding ambiguous real-world user instructions. RealWebAssist includes a dataset of sequential instructions collected from real-world human users. Each user instructs a web-based assistant to perform a series of tasks on multiple websites. A successful agent must reason about the true intent behind each instruction, keep track of the mental state of the user, understand user-specific routines, and ground the intended tasks to actions on the correct GUI elements. Our experimental results show that state-of-the-art models struggle to understand and ground user instructions, posing critical challenges in following real-world user instructions for long-horizon web assistance.

Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies or an indication of political censorship, that is practiced globally by countries, is lacking. Differentiating between safety influenced refusals or politically motivated censorship is hard and unclear. For this purpose we introduce PSP, a dataset built specifically to probe the refusal behaviors in LLMs from an explicitly political context. PSP is built by formatting existing censored content from two data sources, openly available on the internet: sensitive prompts in China generalized to multiple countries, and tweets that have been censored in various countries. We study: 1) impact of political sensitivity in seven LLMs through data-driven (making PSP implicit) and representation-level approaches (erasing the concept of politics); and, 2) vulnerability of models on PSP through prompt injection attacks (PIAs). Associating censorship with refusals on content with masked implicit intent, we find that most LLMs perform some form of censorship. We conclude with summarizing major attributes that can cause a shift in refusal distributions across models and contexts of different countries.

Large Language Models (LLMs) are increasingly being used to plan, reason, and execute tasks across diverse scenarios. In use cases like repeatable workflows and agentic settings, prompts are often reused with minor variations while having a similar structure for recurring tasks. This opens up opportunities for caching. However, exact prompt matching fails on such structurally similar prompts, while semantic caching may produce incorrect responses by ignoring critical differences. To address this, we introduce \ourmethod{}, a generative cache that produces variation-aware responses for structurally similar prompts. \ourmethod{} identifies reusable response patterns across similar prompt structures and synthesizes customized outputs for new requests. We show that \ourmethod{} achieves 83\% cache hit rate, while having minimal incorrect hits on datasets without prompt repetition. In agentic workflows, it improves cache hit rate by $\sim$20\% and reduces end-to-end execution latency by $\sim$34\% compared to standard prompt matching.

Instruction-guided text-to-speech (TTS) research has reached a maturity level where excellent speech generation quality is possible on demand, yet two coupled biases persist: accent bias, where models default to dominant phonetic patterns, and linguistic bias, where dialect-specific lexical and cultural cues are ignored. These biases are interdependent, as authentic accent generation requires both accent fidelity and localized text. We present Contextual Linguistic Adaptation and Retrieval for Inclusive TTS sYnthesis (CLARITY), a backbone-agnostic framework that addresses these biases through dual-signal optimization: (i) contextual linguistic adaptation that localizes input text to the target dialect, and (ii) retrieval-augmented accent prompting (RAAP) that supplies accent-consistent speech prompts. Across twelve English accents, CLARITY improves accent accuracy and fairness while maintaining strong perceptual quality.

Large language model (LLM)-based agents have demonstrated remarkable capabilities in addressing complex tasks, thereby enabling more advanced information retrieval and supporting deeper, more sophisticated human information-seeking behaviors. However, most existing agents operate in a purely reactive manner, responding passively to user instructions, which significantly constrains their effectiveness and efficiency as general-purpose platforms for information acquisition. To overcome this limitation, this paper proposes AppAgent-Pro, a proactive GUI agent system that actively integrates multi-domain information based on user instructions. This approach enables the system to proactively anticipate users' underlying needs and conduct in-depth multi-domain information mining, thereby facilitating the acquisition of more comprehensive and intelligent information. AppAgent-Pro has the potential to fundamentally redefine information acquisition in daily life, leading to a profound impact on human society. Our code is available at: https://github.com/LaoKuiZe/AppAgent-Pro. The demonstration video could be found at: https://www.dropbox.com/scl/fi/hvzqo5vnusg66srydzixo/AppAgent-Pro-demo-video.mp4?rlkey=o2nlfqgq6ihl125mcqg7bpgqu&st=d29vrzii&dl=0.

The task of information extraction (IE) is to extract structured knowledge from text. However, it is often not straightforward to utilize IE output due to the mismatch between the IE ontology and the downstream application needs. We propose a new formulation of IE TEXT2DB that emphasizes the integration of IE output and the target database (or knowledge base). Given a user instruction, a document set, and a database, our task requires the model to update the database with values from the document set to satisfy the user instruction. This task requires understanding user instructions for what to extract and adapting to the given DB/KB schema for how to extract on the fly. To evaluate this new task, we introduce a new benchmark featuring common demands such as data infilling, row population, and column addition. In addition, we propose an LLM agent framework OPAL (Observe-PlanAnalyze LLM) which includes an Observer component that interacts with the database, the Planner component that generates a code-based plan with calls to IE models, and the Analyzer component that provides feedback regarding code quality before execution. Experiments show that OPAL can successfully adapt to diverse database schemas by generating different code plans and calling the required IE models. We also highlight difficult cases such as dealing with large databases with complex dependencies and extraction hallucination, which we believe deserve further investigation. Source code: https://github.com/yzjiao/Text2DB

Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug fixing, they struggle with visually-oriented coding tasks, often producing suboptimal aesthetics. In this paper, we introduce a new pipeline to enhance the aesthetic quality of LLM-generated code. We first construct AesCode-358K, a large-scale instruction-tuning dataset focused on code aesthetics. Next, we propose agentic reward feedback, a multi-agent system that evaluates executability, static aesthetics, and interactive aesthetics. Building on this, we develop GRPO-AR, which integrates these signals into the GRPO algorithm for joint optimization of functionality and code aesthetics. Finally, we develop OpenDesign, a benchmark for assessing code aesthetics. Experimental results show that combining supervised fine-tuning on AesCode-358K with reinforcement learning using agentic reward feedback significantly improves performance on OpenDesign and also enhances results on existing benchmarks such as PandasPlotBench. Notably, our AesCoder-4B surpasses GPT -4o and GPT -4.1, and achieves performance comparable to large open-source models with 480B-685B parameters, underscoring the effectiveness of our approach.Figure 1: Performance comparison of different models on the OpenDesign benchmark.