Chunyu Miao

Liancheng Fang, Aiwei Liu, Henry Peng Zou et al.

Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregressive (AR) LLMs. In practice, however, random-order decoding often hurts generation quality. To mitigate this, low-confidence remasking improves single-sample quality (e.g., Pass@$1$) by prioritizing confident tokens, but it also suppresses exploration and limits multi-sample gains (e.g., Pass@$k$), creating a fundamental quality--exploration dilemma. In this paper, we provide a unified explanation of this dilemma. We show that low-confidence remasking improves a myopic proxy for quality while provably constraining the entropy of the induced sequence distribution. To overcome this limitation, we characterize the optimal distribution that explicitly balances quality and exploration, and develop a simple Independent Metropolis--Hastings sampler that approximately targets this distribution during decoding. Experiments across a range of reasoning benchmarks including MATH500, AIME24/25, HumanEval, and MBPP show that our approach yields better exploration-quality tradeoff than both random and low-confidence remasking.

Chengze Li, Xiao Liu, Hanrong Zhang et al.

Conformal triage converts predictive scores into deployment actions that either release a case, flag it for urgent attention, or defer it to human review. Under prevalence shift, however, the usual summaries of marginal coverage and human-review rate can miss the safety-critical question of whether patients who truly experience the target event are released without review. To address this gap, we introduce a leakage-aware deployment audit for release-side conformal triage. It first assigns target subjects to three non-overlapping roles: prevalence correction, conformal calibration, and held-out release-safety evaluation. This separation then lets the audit evaluate release directly: how many event-positive patients are cleared without review, whether the pilot has enough event labels for calibration, and how the safety-review trade-off shifts. Applying this audit to a retrospective NSCLC pilot shows why lower review can be misleading: after prevalence correction, the pooled conformal branch lowers review by releasing more patients, some of whom are event-positive. Within the audit, the classwise branch acts as a scarcity diagnostic: the pilot has too few event labels to certify safe low-review release.

Weizhi Zhang, Yangning Li, Yuanchen Bei et al. · pku

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.

Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu et al.

Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to hallucinations, difficulty in handling complex tasks, and substantial safety and ethical risks, all of which limit their feasibility and trustworthiness in real-world applications. To overcome these limitations, LLM-based human-agent systems (LLM-HAS) incorporate human-provided information, feedback, or control into the agent system to enhance system performance, reliability and safety. These human-agent collaboration systems enable humans and LLM-based agents to collaborate effectively by leveraging their complementary strengths. This paper provides the first comprehensive and structured survey of LLM-HAS. It clarifies fundamental concepts, systematically presents core components shaping these systems, including environment & profiling, human feedback, interaction types, orchestration and communication, explores emerging applications, and discusses unique challenges and opportunities arising from human-AI collaboration. By consolidating current knowledge and offering a structured overview, we aim to foster further research and innovation in this rapidly evolving interdisciplinary field. Paper lists and resources are available at https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems.

Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang et al.

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution is becoming a core requirement for realistic deployment. However, existing benchmarks largely assume uninterrupted agent behavior or study interruptions only in short, unconstrained language tasks. In this paper, we present the first systematic study of interruptible agents in long-horizon, environmentally grounded web navigation tasks, where actions induce persistent state changes. We formalize three realistic interruption types, including addition, revision, and retraction, and introduce InterruptBench, a benchmark derived from WebArena-Lite that synthesizes high-quality interruption scenarios under strict semantic constraints. Using a unified interruption simulation framework, we evaluate six strong LLM backbones across single- and multi-turn interruption settings, analyzing both their effectiveness in adapting to updated intents and their efficiency in recovering from mid-task changes. Our results show that handling user interruptions effectively and efficiently during long-horizon agentic tasks remains challenging for powerful large-scale LLMs. Code and dataset are available at https://github.com/HenryPengZou/InterruptBench.

Yibo Wang, Congying Xia, Wenting Zhao et al.

Unit test generation has become a promising and important use case of LLMs. However, existing evaluation benchmarks for assessing LLM unit test generation capabilities focus on function- or class-level code rather than more practical and challenging project-level codebases. To address such limitation, we propose ProjectTest, a project-level benchmark for unit test generation covering Python, Java, and JavaScript. ProjectTest features 20 moderate-sized and high-quality projects per language. We evaluate nine frontier LLMs on ProjectTest and the results show that all frontier LLMs tested exhibit moderate performance on ProjectTest on Python and Java, highlighting the difficulty of ProjectTest. We also conduct a thorough error analysis, which shows that even frontier LLMs, such as Claude-3.5-Sonnet, have significant basic yet critical errors, including compilation and cascade errors. Motivated by this observation, we further evaluate all frontier LLMs under manual error-fixing and self-error-fixing scenarios to assess their potential when equipped with error-fixing mechanisms. Our code and dataset is available at \href{https://github.com/YiboWANG214/ProjectTest}{ProjectTest}.

Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu et al.

Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections. They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as credibility, coherence, breadth, depth, and safety. This oversight may result in hazardous or malicious sources being integrated into the final report. To address these issues, we introduce DEEPRESEARCHGUARD, a comprehensive framework featuring four-stage safeguards with open-domain evaluation of references and reports. We assess performance across multiple metrics, e.g., defense success rate and over-refusal rate, and five key report dimensions. In the absence of a suitable safety benchmark, we introduce DRSAFEBENCH, a stage-wise benchmark for deep research safety. Our evaluation spans diverse state-of-the-art LLMs, including GPT-4o, Gemini-2.5-flash, DeepSeek-v3, and o4-mini. DEEPRESEARCHGUARD achieves an average defense success rate improvement of 18.16% while reducing over-refusal rate by 6%. The input guard provides the most substantial early-stage protection by filtering out obvious risks, while the plan and research guards enhance citation discipline and source credibility. Through extensive experiments, we show that DEEPRESEARCHGUARD enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates. The code can be found via https://github.com/Jasonya/DeepResearchGuard.

Wenzhe Fan, Tommaso Tognoli, Henry Peng Zou et al.

Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communication topology during inference, which falls short in many realistic applications where the agents' roles may change \textit{across rounds} due to dynamic adversary, task progression, or time-varying constraints such as communication bandwidth. In this paper, we propose addressing this issue through TodyComm, a \textbf{t}ask-\textbf{o}riented \textbf{dy}namic \textbf{comm}unication algorithm. It produces behavior-driven collaboration topologies that adapt to the dynamics at each round, optimizing the utility for the task through policy gradient. Experiments on five benchmarks demonstrate that under both dynamic adversary and communications budgets, TodyComm delivers superior task effectiveness while retaining token efficiency and scalability.

Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu et al. · tsinghua

Recent improvements in large language models (LLMs) have led many researchers to focus on building fully autonomous AI agents. This position paper questions whether this approach is the right path forward, as these autonomous systems still have problems with reliability, transparency, and understanding the actual requirements of human. We suggest a different approach: LLM-based Human-Agent Systems (LLM-HAS), where AI works with humans rather than replacing them. By keeping human involved to provide guidance, answer questions, and maintain control, these systems can be more trustworthy and adaptable. Looking at examples from healthcare, finance, and software development, we show how human-AI teamwork can handle complex tasks better than AI working alone. We also discuss the challenges of building these collaborative systems and offer practical solutions. This paper argues that progress in AI should not be measured by how independent systems become, but by how well they can work with humans. The most promising future for AI is not in systems that take over human roles, but in those that enhance human capabilities through meaningful partnership.

Hanchen Yang, Jiaqi Wang, Jiannong Cao et al.

Sea surface temperature (SST) prediction is a critical task in ocean science, supporting various applications, such as weather forecasting, fisheries management, and storm tracking. While existing data-driven methods have demonstrated significant success, they often neglect to leverage the rich domain knowledge accumulated over the past decades, limiting further advancements in prediction accuracy. The recent emergence of large language models (LLMs) has highlighted the potential of integrating domain knowledge for downstream tasks. However, the application of LLMs to SST prediction remains underexplored, primarily due to the challenge of integrating ocean domain knowledge and numerical data. To address this issue, we propose Ocean Knowledge Graph-enhanced LLM (OKG-LLM), a novel framework for global SST prediction. To the best of our knowledge, this work presents the first systematic effort to construct an Ocean Knowledge Graph (OKG) specifically designed to represent diverse ocean knowledge for SST prediction. We then develop a graph embedding network to learn the comprehensive semantic and structural knowledge within the OKG, capturing both the unique characteristics of individual sea regions and the complex correlations between them. Finally, we align and fuse the learned knowledge with fine-grained numerical SST data and leverage a pre-trained LLM to model SST patterns for accurate prediction. Extensive experiments on the real-world dataset demonstrate that OKG-LLM consistently outperforms state-of-the-art methods, showcasing its effectiveness, robustness, and potential to advance SST prediction. The codes are available in the online repository.

Chunyu Miao, Henry Peng Zou, Yangning Li et al.

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the iterative and feedback-driven nature of realistic workflows of scientific research development. To address this gap, we present RECODE-H, a benchmark of 102 tasks from research papers and repositories that evaluates LLM agents through multi-turn interactions with LLM-simulated human feedback. It includes structured instructions,unit tests, and a five-level feedback hierarchy to reflect realistic researcher-agent collaboration. We further present ReCodeAgent, a framework that integrates feedback into iterative code generation. Experiments with leading LLMs, including GPT-5, Claude-Sonnet-4, DeepSeek-V3.1, and Gemini 2.5, show substantial performance gains with richer feedback, while also highlighting ongoing challenges in the generation of complex research code. RECODE-H establishes a foundation for developing adaptive, feedback-driven LLM agents in scientific research implementation

Yankai Chen, Xinni Zhang, Yifei Zhang et al.

Brain-Computer Interfaces (BCIs) offer a direct communication pathway between the human brain and external devices, holding significant promise for individuals with severe neurological impairments. However, their widespread adoption is hindered by critical limitations, such as low information transfer rates and extensive user-specific calibration. To overcome these challenges, recent research has explored the integration of Large Language Models (LLMs), extending the focus from simple command decoding to understanding complex cognitive states. Despite these advancements, deploying agentic AI faces technical hurdles and ethical concerns. Due to the lack of comprehensive discussion on this emerging direction, this position paper argues that the field is poised for a paradigm extension from BCI to Brain-Agent Collaboration (BAC). We emphasize reframing agents as active and collaborative partners for intelligent assistance rather than passive brain signal data processors, demanding a focus on ethical data handling, model reliability, and a robust human-agent collaboration framework to ensure these systems are safe, trustworthy, and effective.