SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs

Despite significant advancements in general-purpose AI agents, several challenges still hinder their practical application in real-world scenarios. First, the limited planning capabilities of Large Language Models (LLM) restrict AI agents from effectively solving complex tasks that require long-horizon planning. Second, general-purpose AI agents struggle to efficiently utilize domain-specific knowledge and human expertise. In this paper, we introduce the Standard Operational Procedure-guided Agent (SOP-agent), a novel framework for constructing domain-specific agents through pseudocode-style Standard Operational Procedures (SOPs) written in natural language. Formally, we represent a SOP as a decision graph, which is traversed to guide the agent in completing tasks specified by the SOP. We conduct extensive experiments across tasks in multiple domains, including decision-making, search and reasoning, code generation, data cleaning, and grounded customer service. The SOP-agent demonstrates excellent versatility, achieving performance superior to general-purpose agent frameworks and comparable to domain-specific agent systems. Additionally, we introduce the Grounded Customer Service Benchmark, the first benchmark designed to evaluate the grounded decision-making capabilities of AI agents in customer service scenarios based on SOPs.

Rethinking Model Redundancy for Low-light Image Enhancement

Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images. While recent advancements primarily focus on customizing complex neural network models, we have observed significant redundancy in these models, limiting further performance improvement. In this paper, we investigate and rethink the model redundancy for LLIE, identifying parameter harmfulness and parameter uselessness. Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance: Attention Dynamic Reallocation (ADR) and Parameter Orthogonal Generation (POG). ADR dynamically reallocates appropriate attention based on original attention, thereby mitigating parameter harmfulness. POG learns orthogonal basis embeddings of parameters and prevents degradation to static parameters, thereby mitigating parameter uselessness. Experiments validate the effectiveness of our techniques. We will release the code to the public.

Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising

Image denoising enhances image quality, serving as a foundational technique across various computational photography applications. The obstacle to clean image acquisition in real scenarios necessitates the development of self-supervised image denoising methods only depending on noisy images, especially a single noisy image. Existing self-supervised image denoising paradigms (Noise2Noise and Noise2Void) rely heavily on information-lossy operations, such as downsampling and masking, culminating in low quality denoising performance. In this paper, we propose a novel self-supervised single image denoising paradigm, Positive2Negative, to break the information-lossy barrier. Our paradigm involves two key steps: Renoised Data Construction (RDC) and Denoised Consistency Supervision (DCS). RDC renoises the predicted denoised image by the predicted noise to construct multiple noisy images, preserving all the information of the original image. DCS ensures consistency across the multiple denoised images, supervising the network to learn robust denoising. Our Positive2Negative paradigm achieves state-of-the-art performance in self-supervised single image denoising with significant speed improvements. The code will be released to the public.

Learning to Hash for Recommendation: A Survey

With the explosive growth of users and items, Recommender Systems (RS) are facing unprecedented challenges on both retrieval efficiency and storage cost. Fortunately, Learning to Hash (L2H) techniques have been shown as a promising solution to address the two dilemmas, whose core idea is encoding high-dimensional data into compact hash codes. To this end, L2H for RS (HashRec for short) has recently received widespread attention to support large-scale recommendations. In this survey, we present a comprehensive review of current HashRec algorithms. Specifically, we first introduce the commonly used two-tower models in the recall stage and identify two search strategies frequently employed in L2H. Then, we categorize prior works into two-tier taxonomy based on: (i) the type of loss function and (ii) the optimization strategy. We also introduce some commonly used evaluation metrics to measure the performance of HashRec algorithms. Finally, we shed light on the limitations of the current research and outline the future research directions. Furthermore, the summary of HashRec methods reviewed in this survey can be found at \href{https://github.com/Luo-Fangyuan/HashRec}{https://github.com/Luo-Fangyuan/HashRec}.

Towards the efficacy of federated prediction for epidemics on networks

Epidemic prediction is of practical significance in public health, enabling early intervention, resource allocation, and strategic planning. However, privacy concerns often hinder the sharing of health data among institutions, limiting the development of accurate prediction models. In this paper, we develop a general privacy-preserving framework for node-level epidemic prediction on networks based on federated learning (FL). We frame the spatio-temporal spread of epidemics across multiple data-isolated subnetworks, where each node state represents the aggregate epidemic severity within a community. Then, both the pure temporal LSTM model and the spatio-temporal model i.e., Spatio-Temporal Graph Attention Network (STGAT) are proposed to address the federated epidemic prediction. Extensive experiments are conducted on various epidemic processes using a practical airline network, offering a comprehensive assessment of FL efficacy under diverse scenarios. By introducing the efficacy energy metric to measure system robustness under various client configurations, we systematically explore key factors influencing FL performance, including client numbers, aggregation strategies, graph partitioning, missing infectious reports. Numerical results manifest that STGAT excels in capturing spatio-temporal dependencies in dynamic processes whereas LSTM performs well in simpler pattern. Moreover, our findings highlight the importance of balancing feature consistency and volume uniformity among clients, as well as the prediction dilemma between information richness and intrinsic stochasticity of dynamic processes. This study offers practical insights into the efficacy of FL scenario in epidemic management, demonstrates the potential of FL to address broader collective dynamics.

A Survey on Human-Centric LLMs

The rapid evolution of large language models (LLMs) and their capacity to simulate human cognition and behavior has given rise to LLM-based frameworks and tools that are evaluated and applied based on their ability to perform tasks traditionally performed by humans, namely those involving cognition, decision-making, and social interaction. This survey provides a comprehensive examination of such human-centric LLM capabilities, focusing on their performance in both individual tasks (where an LLM acts as a stand-in for a single human) and collective tasks (where multiple LLMs coordinate to mimic group dynamics). We first evaluate LLM competencies across key areas including reasoning, perception, and social cognition, comparing their abilities to human-like skills. Then, we explore real-world applications of LLMs in human-centric domains such as behavioral science, political science, and sociology, assessing their effectiveness in replicating human behaviors and interactions. Finally, we identify challenges and future research directions, such as improving LLM adaptability, emotional intelligence, and cultural sensitivity, while addressing inherent biases and enhancing frameworks for human-AI collaboration. This survey aims to provide a foundational understanding of LLMs from a human-centric perspective, offering insights into their current capabilities and potential for future development.

Prompt-Guided Internal States for Hallucination Detection of Large Language Models

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes in the structure related to text truthfulness within the LLM's internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods.

A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts

Creativity involves not only generating new ideas from scratch but also redefining existing concepts and synthesizing previous insights. Among various techniques developed to foster creative thinking, brainstorming is widely used. With recent advancements in Large Language Models (LLMs), tools like ChatGPT have significantly impacted various fields by using prompts to facilitate complex tasks. While current research primarily focuses on generating accurate responses, there is a need to explore how prompt engineering can enhance creativity, particularly in brainstorming. Therefore, this study addresses this gap by proposing a framework called GPS, which employs goals, prompts, and strategies to guide designers to systematically work with an LLM tool for improving the creativity of ideas generated during brainstorming. Additionally, we adapted the Torrance Tests of Creative Thinking (TTCT) for measuring the creativity of the ideas generated by AI. Our framework, tested through a design example and a case study, demonstrates its effectiveness in stimulating creativity and its seamless LLM tool integration into design practices. The results indicate that our framework can benefit brainstorming sessions with LLM tools, enhancing both the creativity and usefulness of generated ideas.

Integrated Decision Making and Trajectory Planning for Autonomous Driving Under Multimodal Uncertainties: A Bayesian Game Approach

Modeling the interaction between traffic agents is a key issue in designing safe and non-conservative maneuvers in autonomous driving. This problem can be challenging when multi-modality and behavioral uncertainties are engaged. Existing methods either fail to plan interactively or consider unimodal behaviors that could lead to catastrophic results. In this paper, we introduce an integrated decision-making and trajectory planning framework based on Bayesian game (i.e., game of incomplete information). Human decisions inherently exhibit discrete characteristics and therefore are modeled as types of players in the game. A general solver based on no-regret learning is introduced to obtain a corresponding Bayesian Coarse Correlated Equilibrium, which captures the interaction between traffic agents in the multimodal context. With the attained equilibrium, decision-making and trajectory planning are performed simultaneously, and the resulting interactive strategy is shown to be optimal over the expectation of rivals' driving intentions. Closed-loop simulations on different traffic scenarios are performed to illustrate the generalizability and the effectiveness of the proposed framework.

Multi-modal Integrated Prediction and Decision-making with Adaptive Interaction Modality Explorations

Navigating dense and dynamic environments poses a significant challenge for autonomous driving systems, owing to the intricate nature of multimodal interaction, wherein the actions of various traffic participants and the autonomous vehicle are complex and implicitly coupled. In this paper, we propose a novel framework, Multi-modal Integrated predictioN and Decision-making (MIND), which addresses the challenges by efficiently generating joint predictions and decisions covering multiple distinctive interaction modalities. Specifically, MIND leverages learning-based scenario predictions to obtain integrated predictions and decisions with social-consistent interaction modality and utilizes a modality-aware dynamic branching mechanism to generate scenario trees that efficiently capture the evolutions of distinctive interaction modalities with low variation of interaction uncertainty along the planning horizon. The scenario trees are seamlessly utilized by the contingency planning under interaction uncertainty to obtain clear and considerate maneuvers accounting for multi-modal evolutions. Comprehensive experimental results in the closed-loop simulation based on the real-world driving dataset showcase superior performance to other strong baselines under various driving contexts.