Increased robot deployment, such as in warehousing, has revealed a need for seamless collaboration among heterogeneous robot teams to resolve unforeseen conflicts. To address this challenge, we propose a novel, decentralized framework for robots to request and provide help. The framework begins with robots detecting conflicts using a Vision Language Model (VLM), then reasoning over whether help is needed. If so, it crafts and broadcasts a natural language (NL) help request using a Large Language Model (LLM). Potential helper robots reason over the request and offer help (if able), along with information about impact to their current tasks. Helper reasoning is implemented via an LLM grounded in Signal Temporal Logic (STL) using a Backus-Naur Form (BNF) grammar to guarantee syntactically valid NL-to-STL translations, which are then solved as a Mixed Integer Linear Program (MILP). Finally, the requester robot chooses a helper by reasoning over impact on the overall system. We evaluate our system via experiments considering different strategies for choosing a helper, and find that a requester robot can minimize overall time impact on the system by considering multiple help offers versus simple heuristics (e.g., selecting the nearest robot to help).

Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost-effectiveness compared to human annotation. However, the reliability and security of such systems, particularly their robustness against adversarial manipulations, remain critical concerns. This paper investigates the vulnerability of LLM-as-a-Judge architectures to prompt-injection attacks, where malicious inputs are designed to compromise the judge's decision-making process. We formalize two primary attack strategies: Comparative Undermining Attack (CUA), which directly targets the final decision output, and Justification Manipulation Attack (JMA), which aims to alter the model's generated reasoning. Using the Greedy Coordinate Gradient (GCG) optimization method, we craft adversarial suffixes appended to one of the responses being compared. Experiments conducted on the MT-Bench Human Judgments dataset with open-source instruction-tuned LLMs (Qwen2.5-3B-Instruct and Falcon3-3B-Instruct) demonstrate significant susceptibility. The CUA achieves an Attack Success Rate (ASR) exceeding 30\%, while JMA also shows notable effectiveness. These findings highlight substantial vulnerabilities in current LLM-as-a-Judge systems, underscoring the need for robust defense mechanisms and further research into adversarial evaluation and trustworthiness in LLM-based assessment frameworks.

Mixture-of-experts (MoE) architectures could achieve impressive computational efficiency with expert parallelism, which relies heavily on all-to-all communication across devices. Unfortunately, such communication overhead typically constitutes a significant portion of the total runtime, hampering the scalability of distributed training and inference for modern MoE models (consuming over $40\%$ runtime in large-scale training). In this paper, we first define collaborative communication to illustrate this intrinsic limitation, and then propose system- and algorithm-level innovations to reduce communication costs. Specifically, given a pair of experts co-activated by one token, we call them "collaborated", which comprises $2$ cases as intra- and inter-collaboration, depending on whether they are kept on the same device. Our pilot investigations reveal that augmenting the proportion of intra-collaboration can accelerate expert parallelism at scale. It motivates us to strategically optimize collaborative communication for accelerated MoE training and inference, dubbed Occult. Our designs are capable of either delivering exact results with reduced communication cost or controllably minimizing the cost with collaboration pruning, materialized by modified fine-tuning. Comprehensive experiments on various MoE-LLMs demonstrate that Occult can be faster than popular state-of-the-art inference or training frameworks (more than $1.5\times$ speed up across multiple tasks and models) with comparable or superior quality compared to the standard fine-tuning. Code is available at $\href{https://github.com/UNITES-Lab/Occult}{https://github.com/UNITES-Lab/Occult}$.

Robotic bin packing aids in a wide range of real-world scenarios such as e-commerce and warehouses. Yet, existing works focus mainly on considering the shape of objects to optimize packing compactness and neglect object properties such as fragility, edibility, and chemistry that humans typically consider when packing objects. This paper presents OPA-Pack (Object-Property-Aware Packing framework), the first framework that equips the robot with object property considerations in planning the object packing. Technical-wise, we develop a novel object property recognition scheme with retrieval-augmented generation and chain-of-thought reasoning, and build a dataset with object property annotations for 1,032 everyday objects. Also, we formulate OPA-Net, aiming to jointly separate incompatible object pairs and reduce pressure on fragile objects, while compacting the packing. Further, OPA-Net consists of a property embedding layer to encode the property of candidate objects to be packed, together with a fragility heightmap and an avoidance heightmap to keep track of the packed objects. Then, we design a reward function and adopt a deep Q-learning scheme to train OPA-Net. Experimental results manifest that OPA-Pack greatly improves the accuracy of separating incompatible object pairs (from 52% to 95%) and largely reduces pressure on fragile objects (by 29.4%), while maintaining good packing compactness. Besides, we demonstrate the effectiveness of OPA-Pack on a real packing platform, showcasing its practicality in real-world scenarios.

Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose \texttt{DialogTool}, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) \textit{tool creation}; 2) \textit{tool utilization}: tool awareness, tool selection, tool execution; and 3) \textit{role-consistent response}: response generation and role play. Furthermore, we build \texttt{VirtualMobile} -- an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs\footnote{We will use tools and APIs alternatively, there are no significant differences between them in this paper.}. Taking advantage of these artifacts, we conduct comprehensive evaluation on 13 distinct open- and closed-source LLMs and provide detailed analysis at each stage, revealing that the existing state-of-the-art LLMs still cannot perform well to use tools over long horizons.

Recent advances in test-time scaling suggest that Large Language Models (LLMs) can gain better capabilities by generating Chain-of-Thought reasoning (analogous to human thinking) to respond a given request, and meanwhile exploring more reasoning branches (i.e., generating multiple responses and ensembling them) can improve the final output quality. However, when incorporating the two scaling dimensions, we find that the system efficiency is dampened significantly for two reasons. Firstly, the time cost to generate the final output increases substantially as many reasoning branches would be trapped in the over-thinking dilemma, producing excessively long responses. Secondly, generating multiple reasoning branches for each request increases memory consumption, which is unsuitable for LLM serving since we can only batch a limited number of requests to process simultaneously. To address this, we present SART, a serving framework for efficient and accurate LLM reasoning. The essential idea is to manage the thinking to be short and right, rather than long. For one thing, we devise a redundant sampling with early stopping approach based on empirical observations and theoretic analysis, which increases the likelihood of obtaining short-thinking responses when sampling reasoning branches. For another, we propose to dynamically prune low-quality branches so that only right-thinking branches are maintained, reducing the memory consumption and allowing us to batch more requests. Experimental results demonstrate that SART not only improves the accuracy of LLM reasoning but also enhances the serving efficiency, outperforming existing methods by up to 28.2 times and on average 15.7 times in terms of efficiency when achieving the same level of accuracy.

Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains. However, the ability to selectively forget specific knowledge is critical for ensuring the safety and compliance of deployed models. Existing unlearning efforts typically fine-tune the model with resources such as forget data, retain data, and a calibration model. These additional gradient steps blur the decision boundary between forget and retain knowledge, making unlearning often at the expense of overall performance. To avoid the negative impact of fine-tuning, it would be better to unlearn solely at inference time by safely guarding the model against generating responses related to the forget target, without destroying the fluency of text generation. In this work, we propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation. Specifically, we first employ a prompt classifier to detect unlearning targets and extract the corresponding forbidden token. We then dynamically penalize and filter candidate tokens during generation using a combination of token matching and semantic matching, effectively preventing the model from leaking the forgotten content. Experimental results on copyright content unlearning tasks over the Harry Potter dataset and the MUSE benchmark, as well as entity unlearning tasks on the TOFU dataset, demonstrate that GUARD achieves strong forget quality across various tasks while causing almost no degradation to the LLM's general capabilities, striking an excellent trade-off between forgetting and utility.

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks, spurring research into its underlying mechanisms. However, two primary challenges remain for real-world applications: (1) the lack of quantitative metrics and actionable guidelines for evaluating and optimizing measurable boundaries of CoT capability, and (2) the absence of methods to assess boundaries of unmeasurable CoT capability, such as multimodal perception. To address these gaps, we introduce the Reasoning Boundary Framework++ (RBF++). To tackle the first challenge, we define the reasoning boundary (RB) as the maximum limit of CoT performance. We also propose a combination law for RBs, enabling quantitative analysis and offering actionable guidance across various CoT tasks. For the second challenge, particularly in multimodal scenarios, we introduce a constant assumption, which replaces unmeasurable RBs with scenario-specific constants. Additionally, we propose the reasoning boundary division mechanism, which divides unmeasurable RBs into two sub-boundaries, facilitating the quantification and optimization of both unmeasurable domain knowledge and multimodal perception capabilities. Extensive experiments involving 38 models across 13 tasks validate the feasibility of our framework in cross-modal settings. Additionally, we evaluate 10 CoT strategies, offer insights into optimization and decay from two complementary perspectives, and expand evaluation benchmarks for measuring RBs in LLM reasoning. We hope this work advances the understanding of RBs and optimization strategies in LLMs. Code and data are available at https://github.com/LightChen233/reasoning-boundary.

Large language models are increasingly integrated into news recommendation systems, raising concerns about their role in spreading misinformation. In humans, visual content is known to boost credibility and shareability of information, yet its effect on vision-language models (VLMs) remains unclear. We present the first study examining how images influence VLMs' propensity to reshare news content, whether this effect varies across model families, and how persona conditioning and content attributes modulate this behavior. To support this analysis, we introduce two methodological contributions: a jailbreaking-inspired prompting strategy that elicits resharing decisions from VLMs while simulating users with antisocial traits and political alignments; and a multimodal dataset of fact-checked political news from PolitiFact, paired with corresponding images and ground-truth veracity labels. Experiments across model families reveal that image presence increases resharing rates by 4.8% for true news and 15.0% for false news. Persona conditioning further modulates this effect: Dark Triad traits amplify resharing of false news, whereas Republican-aligned profiles exhibit reduced veracity sensitivity. Of all the tested models, only Claude-3-Haiku demonstrates robustness to visual misinformation. These findings highlight emerging risks in multimodal model behavior and motivate the development of tailored evaluation frameworks and mitigation strategies for personalized AI systems. Code and dataset are available at: https://github.com/3lis/misinfo_vlm

In the age of cloud computing, data privacy protection has become a major challenge, especially when sharing sensitive data across cloud environments. However, how to optimize collaboration across cloud environments remains an unresolved problem. In this paper, we combine federated learning with large-scale language models to optimize the collaborative mechanism of AI systems. Based on the existing federated learning framework, we introduce a cross-cloud architecture in which federated learning works by aggregating model updates from decentralized nodes without exposing the original data. At the same time, combined with large-scale language models, its powerful context and semantic understanding capabilities are used to improve model training efficiency and decision-making ability. We've further innovated by introducing a secure communication layer to ensure the privacy and integrity of model updates and training data. The model enables continuous model adaptation and fine-tuning across different cloud environments while protecting sensitive data. Experimental results show that the proposed method is significantly better than the traditional federated learning model in terms of accuracy, convergence speed and data privacy protection.