Automated Program Repair (APR) agents leverage large language models (LLMs) to autonomously diagnose and patch software bugs using planning, reasoning, and tools. Although these agents show strong performance on leaderboards such as SWE-bench, little is understood about how they take actions, where they fail, and how their behavior compares to human developers. In this paper, we present the first systematic analysis of these limitations using 5 state-of-the-art APR agents. We trace the full decision-making pipelines of the 5 APR agents across 500 real-world repair tasks, from issue description to patch validation. Our study reveals that, while agents excel at simple fixes, they struggle with logic-intensive bugs, often generating verbose, overfitted patches that pass existing test suites without solving the root cause. Test generation and regression test selection remain major bottlenecks, as agents fail to reproduce issues or run relevant regression tests. Moreover, many agents operate with primitive tooling (e.g. bash scripts) and do not have access to debuggers or program analysis tools. These findings highlight key limitations of current APR systems and motivate several directions for next-generation APR design, including but not limited to: (1) a shift-left approach emphasizing early, high-quality test generation and validation to reduce spurious fixes and improve semantic correctness; (2) richer, more integrated tool ecosystems; (3) diversified agent architectures that combine complementary strengths; and (4) benchmarks that prioritize semantic repair quality and test-generation fidelity over surface-level success metrics.
Ira Ceka, Hailie Mitchell, Saurabh Pujar et al.· 0 citations
Multimodal Large Language Models have shown strong performance across multimodal tasks, and recent personalized MLLMs can recognize user-specific concepts and generate contextual captions. However, existing personalized MLLMs mainly focus on isolated concepts, often lacking relational training data, neglecting connections among personalized concepts, and evaluating mostly on recognition or captioning. To address these limitations, we introduce ReGraP, a dataset of 120 personalized knowledge sets, each containing images, knowledge graphs, and Chain-of-Thought Question-Answering pairs. Based on ReGraP, we propose Reasoning enabled Graph-based Personalized Large Language and Vision Assistant ReGraP-LLaVA, a personalized MLLM that incorporates KGs and CoT QA pairs through soft and/or hard graph prompting to align structured relational knowledge with the model's semantic space. We further establish the ReGraP Benchmark, covering multiple-choice, fill-in-the-blank, true/false, and descriptive questions in both open- and closed-ended settings, to evaluate personalized relational reasoning and knowledge-connection capabilities. Experimental results show that ReGraP-LLaVA effectively learns personalized knowledge and performs relational reasoning, achieving the best overall performance among competitive baselines. Code and data are available at: https://github.com/xyfyyds/ReGraP
Yifan Xiang, Zhenxi Zhang, Bin Li et al.· 0 citations
Peripheral neuroblastic tumors (pNTs) are among the most common extracranial solid tumors in children, and accurate pathological subtyping is important for risk stratification and treatment planning. However, pNT subtyping on hematoxylin-eosin whole-slide images (WSIs) remains challenging because of limited pediatric tumor cohorts, marked histological heterogeneity, inter-observer variability, and the computational burden of existing WSI classifiers. To address these challenges, we propose CoPath, a framework consisting of CoHisNet and PathVote. CoHisNet is a lightweight multi-scale feature-fusion network for patch-level histopathological classification. By replacing the multilayer perceptron components in Swin Transformer blocks and the classification head with Kolmogorov-Arnold Network layers, CoHisNet improves nonlinear feature modeling under a compact architecture. Its multi-scale interaction and contrast-driven feature-enhancement design enables the model to capture both tissue-level structures and fine-grained cellular morphology. PathVote further incorporates pathology-informed tissue-component priors to aggregate patch-level predictions into WSI-level decisions. We validated CoPath on a private two-branch PpNTs cohort and the public BreakHis breast cancer histopathology dataset. Experimental results show that CoPath achieves competitive or superior performance compared with general image classifiers, pathology foundation models under linear probing, and pathology-specific classification models, while maintaining substantially lower computational complexity. The source code is available at https://github.com/JSLiam94/CoPath.
Zhu Zhu, Shuo Jiang, Jingyuan Zheng et al.· 0 citations
With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex multi-agent cooperative task scenarios. Multi-agent cooperative decision-making involves multiple agents working together to complete established tasks and achieve specific objectives. These techniques are widely applicable in real-world scenarios such as autonomous driving, drone navigation, disaster rescue, and simulated military confrontations. This paper begins with a comprehensive survey of the leading simulation environments and platforms used for multi-agent cooperative decision-making. Specifically, we provide an in-depth analysis for these simulation environments from various perspectives, including task formats, reward allocation, and the underlying technologies employed. Subsequently, we provide a comprehensive overview of the mainstream intelligent decision-making approaches, algorithms and models for multi-agent systems (MAS). Theseapproaches can be broadly categorized into five types: rule-based (primarily fuzzy logic), game theory-based, evolutionary algorithms-based, deep multi-agent reinforcement learning (MARL)-based, and large language models(LLMs)reasoning-based. Given the significant advantages of MARL andLLMs-baseddecision-making methods over the traditional rule, game theory, and evolutionary algorithms, this paper focuses on these multi-agent methods utilizing MARL and LLMs-based techniques. We provide an in-depth discussion of these approaches, highlighting their methodology taxonomies, advantages, and drawbacks. Further, several prominent research directions in the future and potential challenges of multi-agent cooperative decision-making are also detailed.
Weiqiang Jin, Hongyang Du, Shixiang Tang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult to scale. We investigate whether Multimodal Large Language Models (MLLMs) can assess perceived urban safety from street-view imagery while accounting for the observer-dependent nature of perception. Using Place Pulse 2.0, we evaluate four open and proprietary MLLMs across 56 cities under a Neutral prompt and socio-demographic personas defined by gender, age, and race or ethnicity. We also analyse the keywords generated to justify each classification.
All four models display comparable zero-shot capability, with city-macro F1 scores of 65--69%, and preserve meaningful cross-city variation. However, they systematically favour the Safe class, underpredict unsafety, and compress differences between cities. Their explanations converge on a shared visual lexicon: maintenance, greenery, order, and residential character support Safe judgements, whereas deterioration, isolation, poor lighting, and limited pedestrian activity support Unsafe judgements. Persona prompting produces substantial and structured shifts while holding the image fixed. Female personas yield more Unsafe classifications than Male personas across all models; age effects are model-dependent, although Middle-aged personas generally remain closest to Neutral. Black/African American and Native American personas frequently show the largest departures, while the closest race or ethnicity match varies by model. These findings show that MLLMs can provide scalable signals of perceived urban safety, but not from a demographically neutral standpoint.
Ciro Beneduce, Bruno Lepri, Massimiliano Luca· 0 citations
In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a photo of a <class-name>.''. Purification is the path we choose since it does not require adversarial training on specific attack types and thus can cope with any foreseen attacks. We then formulate purification risk as the KL divergence between the joint distributions of the purification process of denoising the adversarial samples and the attack process of adding perturbations to benign samples, through bidirectional Stochastic Differential Equations (SDEs). The final derived results inspire us to explore purification in the multi-modal latent space of CLIP. We propose two variants for our CLIPure approach: CLIPure-Diff which models the likelihood of images' latent vectors with the DiffusionPrior module in DaLLE-2 (modeling the generation process of CLIP's latent vectors), and CLIPure-Cos which models the likelihood with the cosine similarity between the embeddings of an image and ``a photo of a.''. As far as we know, CLIPure is the first purification method in multi-modal latent space and CLIPure-Cos is the first purification method that is not based on generative models, which substantially improves defense efficiency. We conducted extensive experiments on CIFAR-10, ImageNet, and 13 datasets that previous CLIP-based defense methods used for evaluating zero-shot classification robustness. Results show that CLIPure boosts the SOTA robustness by a large margin, e.g., from 71.7% to 91.1% on CIFAR10, from 59.6% to 72.6% on ImageNet, and 108% relative improvements of average robustness on the 13 datasets over previous SOTA. The code is available at https://github.com/TMLResearchGroup-CAS/CLIPure.
Mingkun Zhang, Keping Bi, Wei Chen et al.· 0 citations
In the present work an efficient border control management procedure is proposed. Compared to operational queue management systems, whose operations are based on mostly static data, the proposed work takes into account dynamic traffic conditions, thus enabling optimal performance, even in cases of uncertainty. To this end, we are proposing a multi-modal Artificial Intelligence (AI) framework, tailored to th needs of border control systems, which enables real-time queue prediction, management, and resource optimization. The novel proposed approach integrates heterogeneous data sources and presents them through a unified representation by employing Long Short-Term Memory (LSTM) networks for queue forecasting. Furthermore, it leverages Model Predictive Control (MPC) and scheduling optimization to derive actionable control policies, which in turn can be presented to border control officers. The proposed work has been evaluated using synthetic data simulating realistic traffic. The evaluation results demonstrate that the proposed method reduces queue prediction error by up to 35% and average waiting time by 30%. Accordingly, the average throughput increases by nearly 20%, compared to ARIMA and rule-based methods. The abovementioned results show the effectiveness and efficiency of combining AI architectures with optimization techniques for proactive and adaptive border traffic management.
Varvara Mama, Eleni Veroni, Nikolaos Kapsalis et al.· 0 citations
User behavior simulation with large language models~(LLMs) is increasingly used to support multi-agent ecosystem simulation. Existing simulators typically rely on static user profiles inferred from historical observations, which become inadequate in socially intensive environments such as live streaming where interaction dynamics continuously reshape user behavior. We propose \textbf{LiveSim}, an LLM-based framework for live-stream ecosystem simulation. It represents users as editable behavioral hypotheses and progressively refines them through trajectory-grounded interactions, where discrepancies between simulated and observed trajectories reveal missing environmental shaping effects. These signals are further extracted as transferable environment-behavior patterns and accumulated in a collective behavioral memory to improve user-level behavioral fidelity and support ecosystem-level simulation. Experiments on real-world live-stream risk-control data validate the effectiveness of LiveSim in improving user-level behavioral fidelity and enabling ecosystem-level analysis of risk evolution and platform intervention effects.
Jiaqi Xu, Yiran Qiao, Jing Chen et al.· 0 citations
Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is difficult because generation, communication and final answer-selection rules usually change simultaneously. We conceptualize multi-agent reasoning as an evolutionary pipeline of candidate generation, peer communication and terminal selection, wherein consensus without quality control can exhibit patterns of memetic drift. We study two questions: (1) when an LLM judge provides effective selection pressure by supplying a signal of answer correctness for candidates generated in a multi-agent system, and (2) when using that signal improves the reported answer. To map judge reliability, we analysed 15,336 questions from MMLU-Pro, GPQA, MedXpertQA and MuSR, with Humanity's Last Exam analysed separately. To test these rules, we replayed 81,390 fixed candidate pools drawn from 16,278 questions across five benchmarks. We report three findings. (1) A correct answer is often already present among the generated candidates, but the system can still converge on and report a wrong answer. (2) Judge reliability is not a fixed trait of the model, but varies with the task, the generator and how rare the correct answer is. (3) Combining answer frequency with the judge's evaluation changed only the final answer-selection rule and raised accuracy from 63.82% to 70.82-70.95%, primarily by rescuing correct answers that were outnumbered by popular errors. In the systems studied here, the value of generating more candidates depends on whether those extra samples make correct answers present, frequent or recognisable. By isolating generation, recognition and selection, these findings establish a diagnostic basis for designing multi-agent architectures that protect generated correct answers from being lost.
Jia-Hao Ji, Si-Jie Li, Jia-Bei Cheng et al.· 0 citations
Graph-based retrieval-augmented generation connects facts that no single passage states, but current implementations pay for that three times: in infrastructure, requiring a vector store, graph database and document store to be kept consistent; in graph quality, because an extraction pipeline that never refuses output fills the graph with edges that assert nothing; and over time, because a graph that only accumulates treats superseded and current facts alike. post-graph-rag is an open-source engine addressing all three. Text chunks with embeddings, a canonical entity graph and community summaries live in one PostgreSQL database, with pgvector for search and edge tables for traversal. Extraction-time invariants run before anything is written: vague predicates, pronominal names and bare quantities are rejected; predicates are normalised onto an optional vocabulary; entities resolve to one vertex per canonical name via model-supplied aliases; and denied relations keep the positive predicate under a negation flag. A temporal layer lets relations carry a validity period from the prose, lets a later document supersede an earlier incompatible assertion from document order alone, and answers as-of queries. Against LightRAG on three corpora under identical extraction and embedding models, post-graph-rag builds a denser graph everywhere, up to $2.4\times$ the relations per entity, and a more queryable one: distinct edge labels run at 0.46 to 0.58 per relation, 0.11 under a controlled vocabulary, against 0.77 to 1.33. It answers comparably with lower query latency, and supports temporal evolution the baseline lacks: 13 and 8 relationships superseded on a novel sequence and a decade of filings, against zero. These are engineering measurements, not a benchmark result. Code: https://github.com/crajah/post-graph-rag, https://github.com/crajah/post-graph
Agents that act on a user's behalf must plan differently for different users, and increasingly do so from some structured representation of user context and not from raw interaction history. How much that structure is worth, and which parts of it carry the value, is largely unmeasured. We introduce SimBench, 47 preference-conditioned planning tasks over 9 synthetic users represented as 28 typed, potentially conflicting context blocks, where the correct plan depends on which contexts are active and how their conflicts are resolved. Against it we evaluate SimGuide, a framework combining typed multi-context representation, explicit conflict arbitration, and optional procedural grounding of individual constraints. Across three models and six user-context representations, SimGuide's typed blocks with arbitration outperform retrieval over the same user's past decisions by +0.210, +0.205 and +0.144 Preference Adherence on Llama 3.3 70B, GPT-4o and Claude Sonnet 4.5 respectively (all p < 0.001); removing the arbitration instruction alone costs up to +0.209. Grounding each constraint with a worked example of past application helps only where the model has headroom: +0.094 on Llama 70B (p < 0.001), falling to +0.029 on GPT-4o and +0.002 on Claude, which already scores perfectly on 35 of 47 tasks without it. We report the benchmark's minimum detectable effect alongside its results. The benchmark ships with a provenance audit that re-derives every reported number from the prompt that produced it.
Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a central property of real-world reference: initial referring expressions are often incomplete or ambiguous, requiring participants to establish shared understanding through interaction. We introduce a controlled evaluation framework for interactive visual grounding in large vision-language models (LVLMs), varying how much target information is provided upfront and how much must be acquired through dialogue. Across four human-grounded visual contexts and four interaction protocols, current LVLMs perform significantly below task-level human baselines. Interaction can help when follow-up questions refine or repair an initial target description. Performance is lowest when no initial description is provided and target information must be acquired through questions, indicating that proactive question-driven grounding remains difficult. LVLMs are also poorly calibrated, often reporting confidence that exceeds their empirical accuracy. Follow-up studies confirm these patterns across varied description sources (human versus AI), reasoning efforts, repeated interactions, description providers, and visual contexts. Overall, interactive visual grounding remains challenging, requiring visual matching, information seeking and synthesis.
