论文检索

General Machine Learning · Everything Else

Yingxu Wang, Shiqi Fan, Mengzhu Wang, Siyang Gao, Chao Wang, nan yin

Knowledge Graph Question Answering (KGQA) aims to interpret natural language queries and perform structured reasoning over knowledge graphs by leveraging their relational and semantic structures to retrieve accurate answers. Existing methods primarily follow either the retrieve-then-reason paradigm, which relies on Graph Neural Networks (GNNs) or heuristic rules to extract static candidate paths, or dynamic path generation strategies that employ large language models (LLMs) with prompting to jointly perform retrieval and reasoning. However, the former lacks adaptability due to static path extraction and the absence of contextual refinement, while the latter suffers from high computational costs and limited evaluation accuracy because of their dependence on fixed scoring functions and repeated LLM calls. To address these issues, this paper proposes Dynamically Adaptive MCTS-based Reasoning (DAMR), a novel framework that integrates LLM-guided Monte Carlo Tree Search (MCTS) with adaptive path evaluation to enable efficient and context-aware KGQA. DAMR leverages MCTS as a backbone, where an LLM-based planner selects the top-k semantically relevant relations at each expansion step to effectively reduce the search space. To enhance evaluation accuracy, we introduce a lightweight Transformer-based scorer that performs context-aware plausibility estimation by jointly encoding the question and relation sequence through cross-attention, thereby capturing fine-grained semantic shifts during multi-hop reasoning. Furthermore, to mitigate the scarcity of high-quality supervision, DAMR incorporates a dynamic pseudo-path refinement mechanism that periodically generates training signals from partial paths explored during search, enabling the scorer to continually adapt to the evolving distribution of reasoning trajectories. Extensive experiments on multiple KGQA benchmarks show that DAMR significantly outperforms state-of-the-art methods.

General Machine Learning · Everything Else

Seong Jin Cho, Gwangsu Kim, Junghyun Lee, Hee Suk Yoon, Joshua Tian Jin Tee, Chang Yoo

Active learning improves training efficiency by selectively querying the most informative samples for labeling. While it naturally fits classification tasks–where informative samples tend to lie near the decision boundary–its application to regression is less straightforward, as information is distributed across the entire dataset. Distance-based sampling is commonly used to promote diversity but tends to overemphasize peripheral regions while neglecting dense, informative interior regions. To address this, we propose a Voronoi-based active learning framework that leverages geometric structure for sample selection. Central to our method is the Voronoi-based Least Disagree Metric (VLDM), which estimates a sample’s proximity to Voronoi faces by measuring how often its cell assignment changes under perturbations of the labeled sites. We further incorporate a distance-based term to capture the periphery and a Voronoi-derived density score to reflect data representativity. The resulting algorithm, *TESSAR* (TESsellation-based Sampling for Active Regression), unifies interior coverage, peripheral exploration, and representativity into a single acquisition score. Experiments on various benchmarks demonstrate that TESSAR consistently achieves competitive or superior performance compared to prior state-of-the-art baselines.

Deep Learning · Everything Else

Tuan-Kiet Doan, Trung-Hieu Tran, Enzo Tartaglione, Nikola Simidjievski, Van-Tam Nguyen

Deep learning has advanced at an unprecedented pace. This progress has led to a significant increase in its complexity. However, despite extensive research on accelerating inference, training deep models directly within a resource-constrained budget remains a considerable challenge due to its high computational and memory requirements. In this paper, we introduce INSTANT (compressIng gradieNtS and acTivAtions for resource-efficieNt Training), a method designed to address both the computational and the memory bottlenecks when training. INSTANT reduces resource demands during backpropagation by projecting gradients and activations into a low-rank subspace and performing computation within that compressed representation. Experimental results demonstrate that INSTANT achieves a $15\times$ reduction in computational cost and $32\times$ reduction in activation memory with negligible impact on model performance. The code will be made publicly available upon the paper's acceptance.

Applications · Everything Else

Zhihao Ding, Jinming Li, Shuai Mu, Jieming Shi

Large language models (LLMs) can solve complex real-world tasks when prompted to generate chain-of-thought (CoT) reasoning, motivating their use for preference reasoning in recommender systems. However, applying LLM reasoning on recommendation faces two practical challenges. First, LLMs struggle to reason over long, noisy user histories that often span hundreds of items while truncation discards signals needed to capture long-term interests. Second, in decoder-only architectures, CoT requires generating rationale tokens autoregressively, leading to prohibitive inference latency for real-world deployment. To address the challenges, we propose SIREN, a framework that enables effective LLM-based rating prediction via long-term interest sketching and internalized reasoning. First, instead of prompting raw histories, we build a compact, token-bounded interest sketch that preserves persistent preferences and suppresses noise. Specifically, we encode and cluster item descriptions to discover semantic topics, then compress each user’s history into a short list of liked and disliked topics, facilitating LLM reasoning. Second, we develop an internalized reasoning strategy for efficient inference. We adopt a two-stage training paradigm: (i) train the LLM to reason explicitly for rating prediction with rule-based reinforcement learning, since ground-truth CoTs are unavailable in recommendation; and (ii) learn to internalize CoT into model parameters through hidden alignment. At inference, the LLM directly generates the rating with near-CoT quality. Extensive experiments show that SIREN reduces average input tokens by $48.7\%$ compared to raw-history prompting, outperforms existing methods while delivering over $100\times$ lower inference latency than CoT-based LLM recommenders. Code and data are available at https://github.com/TommyDzh/SIREN.

Deep Learning · Everything Else

Hanzhu Chen, Lin Yang, Jie Wang, Junhao Yan, Zhe Wang, Xize Liang, Jianye Hao

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, but their high computational costs limit their widespread practical application. We argue that this inefficiency arises from the tight coupling of high-level cognitive planning (devising the solution strategy) and low-level linguistic realization (generating step-by-step text). To address this challenge, we propose a novel collaborative framework that decouples these two processes through Latent Guidance. Our approach implements a division of labor: a large model acts as an Implicit Thinker, performing high-level cognitive planning and compressing its solution strategy into a set of compact latent guidance vectors. A small, efficient model then serves as an Explicit Executor, which receives this latent guidance to generate a concise and effective reasoning chain. This process is enabled by a dual-loss training objective, grounded in information-theoretic principles, where a reconstruction loss explicitly compels the latent guidance to become a high-fidelity representation of the full reasoning chain. Extensive experiments on 8 diverse reasoning benchmarks demonstrate that our method substantially enhances the reasoning capabilities of small models across various scales (from 0.5B to 8B), allowing them to outperform strong baselines and exhibit superior generalization. Notably, our framework boosts small model accuracy by up to 13.9% over its standalone baseline. Our work introduces a new, theoretically-grounded paradigm for empowering small models with large-model thinking, substantially improving the performance-cost trade-off for complex reasoning.

Reinforcement Learning · Everything Else

Bingxiang He, Yuxin Zuo, Zeyuan Liu, Shangziqi Zhao, Zixuan Fu, Junlin Yang, Cheng Qian, Kaiyan Zhang, Yuchen Fan, Ganqu Cui 等

Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground truth labels. Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear. In this work, we revisit URLVR and provide a comprehensive analysis spanning taxonomy, theory and extensive experiments. We first classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework revealing that all intrinsic methods converge toward sharpening the model's initial distribution This sharpening mechanism succeeds when initial confidence aligns with correctness but fails catastrophically when misaligned. Through systematic experiments, we show intrinsic rewards consistently follow a rise-then-fall pattern across methods, with collapse timing determined by model prior rather than engineering choices. Despite these scaling limits, we find intrinsic rewards remain valuable in test-time training on small datasets, and propose Model Collapse Step to measure model prior, serving as a practical indicator for RL trainability. Finally, we explore external reward methods that ground verification in computational asymmetries, showing preliminary evidence they may escape the confidence-correctness ceiling. Our findings chart boundaries for intrinsic URLVR while motivating paths toward scalable alternatives. Code is available at \url{https://github.com/PRIME-RL/TTRL}.

Applications · Everything Else

Yinqi Bai, Jie Wang, Lei Chen, Zhihai Wang, Yumeng Li, Mingxuan Yuan, Jianye Hao, Defu Lian, Enhong Chen

Logic synthesis (LS), which aims to generate a *compact* logic circuit graph with minimized size while *accurately* satisfying a given functionality, plays an important role in chip design. However, existing LS methods struggle to balance circuit structure compactness and functional accuracy, often leading to suboptimal generation. To address this problem, we propose a novel *Circuit Program Evolution* framework, namely CircuitEvo, which iteratively leverages large language models (LLMs) to evolve circuit programs towards improved compactness while preserving functional accuracy. Specifically, CircuitEvo models the circuit graph as a structured program and leverages the strong generative capabilities of LLMs — guided by domain-specific evolutionary prompt strategies — to generate promising circuit candidates in each iteration. Moreover, a structure-aware circuit optimization module is introduced to correct functional discrepancies by appending necessary substructures to the generated circuits. To the best of our knowledge, CircuitEvo is *the first* LLM-based LS approach that can iteratively improve a circuit's compactness while ensuring functional accuracy. Experiments on several widely used benchmarks demonstrate that CircuitEvo can efficiently generate accurate circuits with up to 16 input number and 69 output number. Moreover, our method significantly outperforms state-of-the-art methods in terms of circuit size, achieving an average improvement of 6.74%.

Deep Learning · Everything Else

Manasi Sharma, Chen Bo Calvin Zhang, Chaithanya Bandi, Clinton Wang, Ankit Aich, Huy Nghiem, Tahseen Rabbani, Ye Htet, Brian Jang, Sumana Basu 等

Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities, including multi-step reasoning, cross-document synthesis, and the generation of evidence-backed, long-form answers. Evaluating DR remains challenging because responses are lengthy and diverse, admit many valid solutions, and often depend on dynamic information sources. We introduce ResearchRubrics, a standardized benchmark for DR built with over 2,800+ hours of human labor that pairs realistic, domain-diverse prompts with 2,500+ expert‑written, fine‑grained rubrics to assess factual grounding, reasoning soundness, and clarity. We also propose a new complexity framework for categorizing DR tasks along three axes: conceptual breadth, logical nesting, and exploration. In addition, we develop human and model-based evaluation protocols that measure rubric adherence for DR agents. We evaluate several state‑of‑the‑art DR systems and find that even leading agents like Gemini's DR and OpenAI's DR achieve under 68% average compliance with our rubrics, primarily due to missed implicit context and inadequate reasoning about retrieved information. Our results highlight the need for robust, scalable assessment of deep research capabilities, to which end we release ResearchRubrics (including all prompts, rubrics, and evaluation code) to facilitate progress toward well‑justified research assistants.

Deep Learning · Everything Else

Hengwei Ye, Yuanting Guan, Yuxuan Ge, Tianying Zhu, Yijia Zhong, YiJing Zhang, Han Zhang, Yingna Wu, Zheng Tian

Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enabling them to address a broader range of tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales — an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. Inspired by the Wechsler Intelligence Scales, we introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: execution, perception reasoning, learning, memory, and planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to gauge MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring more accurate and robust evaluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficulty levels to accommodate the rapidly growing MLLM community. Through evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed important limitations of current status. We release our benchmark at: https://kidgym.github.io/KidGym-Website/.

Deep Learning · Everything Else

Ziwen Liu, Huawei Lin, Yide Ran, Denghui Zhang, Jianwen Xie, Chuan Li, Weijie Zhao, Zhaozhuo Xu

Large language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focused largely on optimization methods that adjust parameters to enforce forgetting while preserving retention. However, these approaches assume that the forget and retain sets are readily available, which rarely holds in practice. Unlearning is typically triggered by an undesired generation at inference time, making the retrieval of relevant data the central challenge. We introduce the notion of data Pareto improvement for LLM unlearning, which formalizes how retrieval can expand the achievable trade-off frontier between forgetting and retention. To realize this principle, we propose Randomized Antipodal Search on Linearized Influence Kernel (RASLIK), a retrieval algorithm that combines permutation–projection hashing with randomized antipodal search. RASLIK reduces selection variance, achieves sublinear complexity, and yields a double gain in both quality and efficiency. Across multiple models, datasets, and unlearning algorithms, RASLIK consistently outperforms deterministic baselines and even oracle sampling, establishing randomized search as a principled and scalable solution for data-centric unlearning.

Deep Learning · Everything Else

Peiming Li, Zhiyuan Hu, Shiyu Li, Xi Chen, Yang Tang

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a structured reasoning process. First, to bridge the preference inference gap, we introduce the DeepPref benchmark. This dataset, comprising 3000 preference-query pairs across 20 topics, is curated by simulating a multi-faceted cognitive council that produces critique-annotated reasoning chains to deconstruct query semantics and reveal latent risks. Second, to instill defensive reasoning, we introduce the Personalized Generative Process Reward Model (Pers-GenPRM), which frames reward modeling as a personalized reasoning task. It generates a critique chain to evaluate a response's alignment with user preferences before outputting a final score based on this rationale. Ultimately, this interpretable, structured reward signal guides policy model through Critique-Driven Policy Alignment, a process-level online reinforcement learning algorithm integrating both numerical and natural language feedback. Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning. Our dataset is available at \url{https://DeepPref.github.io/}.

Deep Learning · Everything Else

Fan Shi, Yuxuan Liang, Xiaolei Chen, Haiyang Yu, Xu Li, Yi Zheng, Rui Zhu, Xiangyang Xue, Bin Li

Human cognition is compositional, and one can parse a visual scene into independent concepts and the corresponding concept-changing rules. By contrast, many vision-language systems process images holistically, with limited support for explicit decomposition. Previous methods of decomposing concepts and rules often rely on hand-crafted inductive biases or human-designed priors. We introduce a Concept-Rule Decomposition (CRD) framework to decompose concept-level rules with Large Vision-Language Models (LVLMs), which explains visual input by leveraging LVLM-extracted concepts and the rules governing their variation. The proposed method operates in two stages: (1) a pretrained LVLM proposes visual concepts and concept values, which are employed to instantiate a space of concept rule functions that model concept changes and spatial distributions; (2) an iterative process to select a concise set of concepts that best account for the input according to the rule function. We evaluate CRD on an abstract visual reasoning benchmark, a spatial reasoning benchmark, and a real-world image caption dataset. Across both settings, our approach outperforms baseline models while improving interpretability by explicitly revealing underlying concepts and compositional rules, advancing explainable and generalizable visual reasoning.

General Machine Learning · Everything Else

Wei Wang, Tianhao Ma, Ming-Kun Xie, Gang Niu, Masashi Sugiyama

Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data. In partial multi-label learning, each instance is annotated with a candidate label set, among which only some labels are relevant; in complementary multi-label learning, each instance is annotated with complementary labels indicating the classes to which the instance does not belong. Existing consistent approaches for the two paradigms either require accurate estimation of the generation process of candidate or complementary labels or assume a uniform distribution to eliminate the estimation problem. However, both conditions are usually difficult to satisfy in real-world scenarios. In this paper, we propose consistent approaches that do not rely on the aforementioned conditions to handle both problems in a unified way. Specifically, we propose two risk estimators based on first- and second-order strategies. Theoretically, we prove consistency w.r.t. two widely used multi-label classification evaluation metrics and derive convergence rates for the estimation errors of the proposed risk estimators. Empirically, extensive experimental results on both real-world and synthetic datasets validate the effectiveness of our proposed approaches against state-of-the-art methods.

Applications · Everything Else

Jiedong Jiang, Wanyi He, Wang Yuefeng, Guoxiong Gao, Yongle Hu, Jingting Wang, Nailin Guan, Peihao Wu, Bryan Dai, Liang Xiao 等

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in formal theorem proving, particularly on contest-based mathematical benchmarks like the IMO. However, these contests do not reflect the depth, breadth, and abstraction of modern mathematical research. To bridge this gap, we introduce **FATE**, a new benchmark series in formal algebra designed to chart a course toward advanced mathematical reasoning. We present two new components, FATE-H and FATE-X, each with 100 problems in abstract and commutative algebra. The FATE series spans a difficulty spectrum from undergraduate exercises to problems exceeding PhD qualifying exams. Notably, FATE-X is the first formal benchmark to surpass both PhD-level exam difficulty and the coverage of the Mathlib library. Our evaluations of state-of-the-art LLM provers on this new benchmark reveal a stark performance gap compared to contest math: the best model achieves only 3\% (pass@64) accuracy on FATE-H and 0\% on FATE-X. Our two-stage evaluation reveals that models' natural-language reasoning is notably more accurate than their ability to formalize this reasoning. We systematically classify the common errors that arise during this formalization process. Furthermore, a comparative study shows that a specialized prover can exhibit less effective reflection than general-purpose models, reducing its accuracy at the natural-language stage. We believe FATE provides a robust and challenging benchmark that establishes essential checkpoints on the path toward research-level formal mathematical reasoning.

Deep Learning · Everything Else

Akira Ito, Masanori Yamada, Daiki Chijiwa, Atsutoshi Kumagai

Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input–output behavior allows the two models to be connected by a low-loss linear path. When such a path exists, the models are said to achieve linear mode connectivity (LMC). Prior studies, including Ainsworth et al. (2023), have reported that achieving LMC requires not only an appropriate permutation search but also sufficiently wide models (e.g., a 32 $\times$ width multiplier for ResNet-20). This is broadly believed to be because increasing the model width ensures a large enough space of candidate permutations, increasing the chance of finding one that yields LMC. In this work, we empirically demonstrate that, __even without any permutations__, simply widening the models is sufficient for achieving LMC when using a suitable softmax temperature calibration. We further explain why this phenomenon arises by analyzing intermediate layer outputs. Specifically, we introduce layerwise exponentially weighted connectivity (LEWC), which states that the output of each layer of the merged model can be represented as an exponentially weighted sum of the outputs of the corresponding layers of the original models. Consequently the merged model's output matches that of an ensemble of the original models, facilitating LMC. To the best of our knowledge, this work is the first to show that widening the model not only facilitates __nonlinear__ mode connectivity, as suggested in prior research, but also significantly increases the possibility of achieving __linear__ mode connectivity.

Deep Learning · Everything Else

Zichen Wen, Jiashu Qu, Zhaorun Chen, Xiaoya Lu, Dongrui Liu, Zhiyuan Liu, Ruixi Wu, Yicun Yang, Xiangqi Jin, Haoyun Xu 等

Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parallel decoding and bidirectional modeling. However, despite strong performance in code generation and text infilling, we identify a fundamental safety concern: existing alignment mechanisms fail to safeguard dLLMs against context-aware, masked-input adversarial prompts, exposing novel vulnerabilities. To this end, we present **DIJA**, the first systematic study and jailbreak attack framework that exploits unique safety weaknesses of dLLMs. Specifically, our proposed DIJA constructs adversarial interleaved mask-text prompts that exploit the text generation mechanisms of dLLMs, i.e., bidirectional modeling and parallel decoding. Bidirectional modeling drives the model to produce contextually consistent outputs for masked spans, even when harmful, while parallel decoding limits model dynamic filtering and rejection sampling of unsafe content. This causes standard alignment mechanisms to fail, enabling harmful completions in alignment-tuned dLLMs, even when harmful behaviors or unsafe instructions are directly exposed in the prompt. Through comprehensive experiments, we demonstrate that DIJA significantly outperforms existing jailbreak methods, exposing a previously overlooked threat surface in dLLM architectures. Notably, our method achieves up to 100\% keyword-based ASR on Dream-Instruct, surpassing the strongest prior baseline, ReNeLLM, by up to 78.5\% in evaluator-based ASR on JailbreakBench and by 37.7 points in StrongREJECT score, while requiring no rewriting or hiding of harmful content in the jailbreak prompt. Our findings underscore the urgent need for rethinking safety alignment in this emerging class of language models. Code is available at https://github.com/ZichenWen1/DIJA.

Applications · Everything Else

Xiaoxue Ren, Penghao Jiang, Kaixin Li, Zhiyong Huang, Xiaoning Du, Jiaojiao Jiang, Zhenchang Xing, Jiamou Sun, Terry Yue Zhuo

Web applications are prime targets for cyberattacks due to their role as entry points to vital services and sensitive data repositories. Traditional penetration testing is expensive and requires specialized expertise, creating scalability challenges for securing the expanding web ecosystem. While language model agents have shown promise in certain cybersecurity tasks, modern web applications require visual understanding of complex user interfaces, dynamic content rendering, and multi-step interactive workflows that only computer-use agents (CUAs) can handle. Despite CUAs' demonstrated capabilities in web browsing and visual task automation, their potential to discover and exploit web application vulnerabilities through graphical interfaces remains unknown. We introduce HackWorld, the first evaluation framework for systematically assessing CUAs' capabilities in exploiting web application vulnerabilities through visual interaction. Unlike existing benchmarks using sanitized environments, HackWorld exposes CUAs to 36 curated applications spanning 11 frameworks and 7 languages, containing realistic vulnerabilities including injection flaws, authentication bypasses, and unsafe input handling. Our framework directly evaluates CUAs' ability to discover and exploit these vulnerabilities using Capture-the-Flag (CTF) methodology while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals exploitation rates below 12%, struggling to plan multi-step attacks and use security tools effectively. Our results expose CUAs' limited cybersecurity skills when operating on vulnerable web applications, opening future research directions on developing security-aware CUAs for vulnerability detection and exploitation.

Deep Learning · Everything Else

Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun, Gitta Kutyniok

We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignment. GradPCA applies Principal Component Analysis (PCA) to gradient class-means, achieving more consistent performance than existing methods across standard image classification benchmarks. We provide a theoretical perspective on spectral OOD detection in neural networks to support GradPCA, highlighting feature-space properties that enable effective detection and naturally emerge from NTK alignment. Our analysis further reveals that feature quality—particularly the use of pretrained versus non-pretrained representations—plays a crucial role in determining which detectors will succeed. Extensive experiments validate the strong performance of GradPCA, and our theoretical framework offers guidance for designing more principled spectral OOD detectors.

Deep Learning · Everything Else

Myoung Hoon Ha, Hyunjun Kim, Yoondo Sung, Youngha Jo, Min Kang, Sang Wan Lee

Predictive Coding Networks (PCNs) offer a biologically inspired alternative to conventional deep neural networks. However, their scalability is hindered by severe training instabilities that intensify with network depth. Through dynamical mean-field analyses, we identify two fundamental pathologies that impede deep PCN training: (1) prediction error (PE) imbalance that leads to uneven learning across layers, characterized by error concentration at network boundaries; and (2) exploding and vanishing prediction errors (EVPE) sensitive to weight variance. To address these challenges, we propose Meta-PCN, a unified framework that incorporates two synergistic components: (1) a loss based on meta-prediction error, which minimizes PEs of PEs to linearize the nonlinear inference dynamics; and (2) weight regularization that employs normalization to regulate weight variance and mitigate EVPE. Extensive experimental validation on CIFAR-10/100 and TinyImageNet demonstrates that Meta-PCN \rev{achieves} statistically significant improvements over conventional PCNs, outperforming backpropagation in most tested configurations, while preserving the local learning rules of PCNs.

Deep Learning · Everything Else

Ming Ma, Jue Zhang, Fangkai Yang, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Large language model (LLM)–based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. On the datasets derived from GAIA and AssistantBench, DoVer flips 18–28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. Our findings highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems.