R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation

Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (R-Bench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing in both English and Chinese. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and crosslinguistic alignment, enabling the assessment to be an Olympiad-level multi-disciplinary benchmark. We evaluate widely used models, including OpenAI o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available at here.

MATCHA: Can Multi-Agent Collaboration Build a Trustworthy Conversational Recommender?

In this paper, we propose a multi-agent collaboration framework called MATCHA for conversational recommendation system, leveraging large language models (LLMs) to enhance personalization and user engagement. Users can request recommendations via free-form text and receive curated lists aligned with their interests, preferences, and constraints. Our system introduces specialized agents for intent analysis, candidate generation, ranking, re-ranking, explainability, and safeguards. These agents collaboratively improve recommendations accuracy, diversity, and safety. On eight metrics, our model achieves superior or comparable performance to the current state-of-the-art. Through comparisons with six baseline models, our approach addresses key challenges in conversational recommendation systems for game recommendations, including: (1) handling complex, user-specific requests, (2) enhancing personalization through multi-agent collaboration, (3) empirical evaluation and deployment, and (4) ensuring safe and trustworthy interactions.

On the Price of Differential Privacy for Hierarchical Clustering

Hierarchical clustering is a fundamental unsupervised machine learning task with the aim of organizing data into a hierarchy of clusters. Many applications of hierarchical clustering involve sensitive user information, therefore motivating recent studies on differentially private hierarchical clustering under the rigorous framework of Dasgupta's objective. However, it has been shown that any privacy-preserving algorithm under edge-level differential privacy necessarily suffers a large error. To capture practical applications of this problem, we focus on the weight privacy model, where each edge of the input graph is at least unit weight. We present a novel algorithm in the weight privacy model that shows significantly better approximation than known impossibility results in the edge-level DP setting. In particular, our algorithm achieves $O(\log^{1.5}n/\varepsilon)$ multiplicative error for $\varepsilon$-DP and runs in polynomial time, where $n$ is the size of the input graph, and the cost is never worse than the optimal additive error in existing work. We complement our algorithm by showing if the unit-weight constraint does not apply, the lower bound for weight-level DP hierarchical clustering is essentially the same as the edge-level DP, i.e. $\Omega(n^2/\varepsilon)$ additive error. As a result, we also obtain a new lower bound of $\tilde{\Omega}(1/\varepsilon)$ additive error for balanced sparsest cuts in the weight-level DP model, which may be of independent interest. Finally, we evaluate our algorithm on synthetic and real-world datasets. Our experimental results show that our algorithm performs well in terms of extra cost and has good scalability to large graphs.

GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning

Geometry problem-solving (GPS), a challenging task requiring both visual comprehension and symbolic reasoning, effectively measures the reasoning capabilities of multimodal large language models (MLLMs). Humans exhibit strong reasoning ability in this task through accurate identification and adaptive application of geometric principles within visual contexts. However, existing benchmarks fail to jointly assess both dimensions of the human-like geometric reasoning mechanism in MLLMs, remaining a critical gap in assessing their ability to tackle GPS. To this end, we introduce GeoSense, the first comprehensive bilingual benchmark designed to systematically evaluate the geometric reasoning abilities of MLLMs through the lens of geometric principles. GeoSense features a five-level hierarchical framework of geometric principles spanning plane and solid geometry, an intricately annotated dataset of 1,789 problems, and an innovative evaluation strategy. Through extensive experiments on GeoSense with various open-source and closed-source MLLMs, we observe that Gemini-2.0-pro-flash performs best, achieving an overall score of $65.3$. Our in-depth analysis reveals that the identification and application of geometric principles remain a bottleneck for leading MLLMs, jointly hindering their reasoning abilities. These findings underscore GeoSense's potential to guide future advancements in MLLMs' geometric reasoning capabilities, paving the way for more robust and human-like reasoning in artificial intelligence.

Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models

Learning to perform manipulation tasks from human videos is a promising approach for teaching robots. However, many manipulation tasks require changing control parameters during task execution, such as force, which visual data alone cannot capture. In this work, we leverage sensing devices such as armbands that measure human muscle activities and microphones that record sound, to capture the details in the human manipulation process, and enable robots to extract task plans and control parameters to perform the same task. To achieve this, we introduce Chain-of-Modality (CoM), a prompting strategy that enables Vision Language Models to reason about multimodal human demonstration data -- videos coupled with muscle or audio signals. By progressively integrating information from each modality, CoM refines a task plan and generates detailed control parameters, enabling robots to perform manipulation tasks based on a single multimodal human video prompt. Our experiments show that CoM delivers a threefold improvement in accuracy for extracting task plans and control parameters compared to baselines, with strong generalization to new task setups and objects in real-world robot experiments. Videos and code are available at https://chain-of-modality.github.io

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee constraint satisfaction outside their training distribution due to their reliance on implicit, post-hoc preferences. Inspired by a paradigm shift to first curate data before tuning, we introduce a new framework for safe language alignment that learns natural language constraints from positive and negative demonstrations as a primary step. From inferring both a task-specific reward function and latent constraint functions, our approach fosters adaptation to novel safety requirements and robust generalization under domain shifts and adversarial inputs. We formalize the framework within a Constrained Markov Decision Process (CMDP) and validate it via a text-based navigation environment, demonstrating safe adaptation to changing danger zones. Our experiments show fewer violations upon domain shift when following a safe navigation path, and we achieve zero violations by applying learned constraints to a distilled BERT model as a fine-tuning technique. This work offers a promising path toward building safety-critical and more generalizable LLMs for practical NLP settings.

Automating Personalization: Prompt Optimization for Recommendation Reranking

Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.

A novel gesture interaction control method for rehabilitation lower extremity exoskeleton

With the rapid development of Rehabilitation Lower Extremity Robotic Exoskeletons (RLEEX) technology, significant advancements have been made in Human-Robot Interaction (HRI) methods. These include traditional physical HRI methods that are easily recognizable and various bio-electrical signal-based HRI methods that can visualize and predict actions. However, most of these HRI methods are contact-based, facing challenges such as operational complexity, sensitivity to interference, risks associated with implantable devices, and, most importantly, limitations in comfort. These challenges render the interaction less intuitive and natural, which can negatively impact patient motivation for rehabilitation. To address these issues, this paper proposes a novel non-contact gesture interaction control method for RLEEX, based on RGB monocular camera depth estimation. This method integrates three key steps: detecting keypoints, recognizing gestures, and assessing distance, thereby applying gesture information and augmented reality triggering technology to control gait movements of RLEEX. Results indicate that this approach provides a feasible solution to the problems of poor comfort, low reliability, and high latency in HRI for RLEEX platforms. Specifically, it achieves a gesture-controlled exoskeleton motion accuracy of 94.11\% and an average system response time of 0.615 seconds through non-contact HRI. The proposed non-contact HRI method represents a pioneering advancement in control interactions for RLEEX, paving the way for further exploration and development in this field.

Get the Agents Drunk: Memory Perturbations in Autonomous Agent-based Recommender Systems

Large language model-based agents are increasingly used in recommender systems (Agent4RSs) to achieve personalized behavior modeling. Specifically, Agent4RSs introduces memory mechanisms that enable the agents to autonomously learn and self-evolve from real-world interactions. However, to the best of our knowledge, how robust Agent4RSs are remains unexplored. As such, in this paper, we propose the first work to attack Agent4RSs by perturbing agents' memories, not only to uncover their limitations but also to enhance their security and robustness, ensuring the development of safer and more reliable AI agents. Given the security and privacy concerns, it is more practical to launch attacks under a black-box setting, where the accurate knowledge of the victim models cannot be easily obtained. Moreover, the practical attacks are often stealthy to maximize the impact. To this end, we propose a novel practical attack framework named DrunkAgent. DrunkAgent consists of a generation module, a strategy module, and a surrogate module. The generation module aims to produce effective and coherent adversarial textual triggers, which can be used to achieve attack objectives such as promoting the target items. The strategy module is designed to `get the target agents drunk' so that their memories cannot be effectively updated during the interaction process. As such, the triggers can play the best role. Both of the modules are optimized on the surrogate module to improve the transferability and imperceptibility of the attacks. By identifying and analyzing the vulnerabilities, our work provides critical insights that pave the way for building safer and more resilient Agent4RSs. Extensive experiments across various real-world datasets demonstrate the effectiveness of DrunkAgent.

SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite substantial advancements, prior approaches often address each of these tasks independently, with separate models focused on individual issues. However, this isolated approach fails to account for the fact that defects like incompleteness, low resolution, noise, and lack of color frequently coexist, with each defect influencing and correlating with the others. Simply applying these models sequentially can lead to error accumulation from each model, along with increased computational costs. To address these challenges, we introduce SuperPC, the first unified diffusion model capable of concurrently handling all four tasks. Our approach employs a three-level-conditioned diffusion framework, enhanced by a novel spatial-mix-fusion strategy, to leverage the correlations among these four defects for simultaneous, efficient processing. We show that SuperPC outperforms the state-of-the-art specialized models as well as their combination on all four individual tasks.