论文检索

Deep Learning · Everything Else

Xinhao Yao, Ruifeng Ren, Yun Liao, Lizhong Ding, Yong Liu

Chain-of-Thought (CoT) training has markedly advanced the reasoning capabilities of large language models (LLMs), yet the mechanisms by which CoT training enhances generalization remain inadequately understood. In this work, we demonstrate that compositional generalization is fundamental: models systematically combine simpler learned skills during CoT training to address novel and more complex problems. Through a theoretical and structural analysis, we formalize this process: 1) Theoretically, the information-theoretic generalization bounds through distributional divergence can be decomposed into in-distribution (ID) and out-of-distribution (OOD) components. Specifically, the non-CoT models fail on OOD tasks due to unseen compositional patterns, whereas CoT-trained models achieve strong generalization by composing previously learned skills. In addition, controlled experiments and real-world validation confirm that CoT training accelerates convergence and enhances generalization from ID to both ID and OOD scenarios while maintaining robust performance even with tolerable noise. 2) Structurally, CoT training internalizes reasoning into a two-stage compositional circuit, where the number of stages corresponds to the explicit reasoning steps during training. Notably, CoT-trained models resolve intermediate results at shallower layers compared to non-CoT counterparts, freeing up deeper layers to specialize in subsequent reasoning steps. A key insight is that CoT training teaches models how to think—by fostering compositional reasoning—rather than merely what to think, through the provision of correct answers alone. This paper offers valuable insights for designing CoT strategies to enhance LLMs' reasoning robustness.

General Machine Learning · Probabilistic Methods

Brendan Ross, Noël Vouitsis, Atiyeh Ashari Ghomi, Rasa Hosseinzadeh, Ji Xin, Zhaoyan Liu, Yi Sui, Shiyi Hou, Kin Kwan Leung, Gabriel Loaiza-Ganem 等

Although large language models (LLMs) are becoming increasingly capable of solving challenging real-world tasks, accurately quantifying their uncertainty remains a critical open problem—one that limits their applicability in high-stakes domains. This challenge is further compounded by the closed-source, black-box nature of many state-of-the-art LLMs. Moreover, LLM-based systems can be highly sensitive to the prompts that bind them together, which often require significant manual tuning (i.e., prompt engineering). In this work, we address these challenges by viewing LLM-based systems through a Bayesian lens. We interpret prompts as textual parameters in a statistical model, allowing us to use a small training dataset to perform Bayesian inference over these prompts. This novel perspective enables principled uncertainty quantification over both the model’s textual parameters and its downstream predictions, while also incorporating prior beliefs about these parameters expressed in free-form text. To perform Bayesian inference— a difficult problem even for well-studied data modalities—we introduce Metropolis-Hastings through LLM Proposals (MHLP), a novel Markov chain Monte Carlo (MCMC) algorithm that combines prompt optimization techniques with standard MCMC methods. MHLP is a turnkey modification to existing LLM pipelines, including those that rely exclusively on closed-source models. Empirically, we demonstrate that our method yields improvements in both predictive accuracy and uncertainty quantification (UQ) on a range of LLM benchmarks and UQ tasks. More broadly, our work demonstrates a viable path for incorporating methods from the rich Bayesian literature into the era of LLMs, paving the way for more reliable and calibrated LLM-based systems.

Optimization · Large Scale, Parallel and Distributed

Shuhua Yu, Dusan Jakovetic, Soummya Kar

Heavy-tailed noise in nonconvex stochastic optimization has garnered increasing research interest, as empirical studies, including those on training attention models, suggest it is a more realistic gradient noise condition. This paper studies first-order nonconvex stochastic optimization under heavy-tailed gradient noise in a decentralized setup, where each node can only communicate with its direct neighbors in a predefined graph. Specifically, we consider a class of heavy-tailed gradient noise that is zero-mean and has only $p$-th moment for $p \in (1, 2]$. We propose GT-NSGDm, Gradient Tracking based Normalized Stochastic Gradient Descent with momentum, that utilizes normalization, in conjunction with gradient tracking and momentum, to cope with heavy-tailed noise on distributed nodes. We show that, when the communication graph admits primitive and doubly stochastic weights, GT-NSGDm guarantees, for the first time in the literature, that the expected gradient norm converges at an optimal non-asymptotic rate $O\big(1/T^{(p-1)/(3p-2)}\big)$, which matches the lower bound in the centralized setup. When the tail index $p$ is unknown, GT-NSGDm attains a non-asymptotic rate $O\big( 1/T^{(p-1)/(2p)} \big)$ that is, for $p < 2$, topology independent and has a speedup factor $n^{1-1/p}$ in terms of the number of nodes $n$. Finally, experiments on nonconvex linear regression with tokenized synthetic data and decentralized training of language models on a real-world corpus demonstrate that GT-NSGDm is more robust and efficient than baselines.

Reinforcement Learning · Deep RL

Yaoyu Wang, Hankun Dai, Zhidong Yang, Junmin Xiao, Guangming Tan

Code generation is a crucial research area in the field of artificial intelligence, holding the potential to revolutionize software development and streamline programming processes. However, generating the high-performance code, which need to be executed in a shorter time for the low-latency scenario, remains a formidable challenge. Existing methods often struggle to account for the irregularity of input sparse data in sparse programs and the need for domain-specific architectural knowledge, leading to sub-optimal performance. To tackle these issues, we propose the SparseRL framework. SparseRL leverages deep reinforcement learning, treating a pre-trained language model as a stochastic policy. It takes the row and column indices of non-zero elements in the sparse matrix as input and generates CUDA code as output for sparse matrix operations. We also introduce a domain-specific code generation mechanism for the dynamic input, a sinusoidal embedding technique tailored for sparse matrices, and a hierarchical reward function that considers both code correctness and execution efficiency. Experimental results demonstrate SparseRL achieves state-of-the-art performance. In sparse matrix-vector multiplication (SpMV) tasks, it improves the compilation rate by 20% compared to existing methods, and the generated code runs 30% faster on average. For sparse matrix-dense matrix multiplication (SpMM) tasks, SparseRL also shows significant performance gains. These results highlight the effectiveness of SparseRL in generating high-performance CUDA code for sparse matrix operations.

Theory · Interpretability and Visualization

Eric Alsmann, Lowejatan Noori, Martin Lange

We investigate the expressive power of state space models (SSM), which have recently emerged as a potential alternative to transformer architectures in large language models. Building on recent work, we analyse SSM expressiveness through fragments and extensions of linear temporal logic over finite traces. Our results show that the expressive capabilities of SSM vary substantially depending on the underlying gating mechanism. We further distinguish between SSM operating over fixed-width arithmetic (quantised models), whose expressive power remains within regular languages, and SSM with unbounded precision, which can capture counting properties and non-regular languages. In addition, we provide a systematic comparison between these different SSM variants and known results on transformers, thereby clarifying how the two architectures relate in terms of expressive power.

Reinforcement Learning · Multi-agent

Eugenie Lai, Gerardo Vitagliano, Ziyu Zhang, Om Chabra, SIVAPRASAD SUDHIR, Anna Zeng, Anton Zabreyko, Chenning Li, Ferdi Kossmann, Jialin Ding 等

Discovering insights from a real-world data lake potentially containing unclean, semi-structured, and unstructured data requires a variety of data processing tasks, ranging from extraction and cleaning to integration, analysis, and modeling. This process often also demands domain knowledge and project-specific insight. While AI models have shown remarkable results in reasoning and code generation, their abilities to design and execute complex pipelines that solve these data-lake-to-insight challenges remain unclear. We introduce KramaBench which consists of 104 manually curated and solved challenges spanning 1700 files, 24 data sources, and 6 domains. KramaBench focuses on testing the end-to-end capabilities of AI systems to solve challenges which require automated orchestration of different data tasks. KramaBench also features a comprehensive evaluation framework assessing the pipeline design and individual data task implementation abilities of AI systems. We evaluate 8 LLMs using our single-agent reference framework DS-Guru, alongside both open- and closed-source single- and multi-agent systems, and find that while current agentic systems may handle isolated data-science tasks and generate plausible draft pipelines, they struggle with producing working end-to-end pipelines. On KramaBench, the best system reaches only 55% end-to-end accuracy in the full data-lake setting. Even with perfect retrieval, the accuracy tops out at 62%. Leading LLMs can identify up to 42% of important data tasks but can only fully implement 20% of individual data tasks.

Guozhang Li, Xinran Duan, Mei Wang, Lizhi Wang, Hua Huang

Fine-grained temporal action segmentation plays a vital role in comprehensivehuman behavior understanding, with skeleton-based approaches (STAS) gaining prominence for their privacy and robustness. A core challenge in STAS arises from the conflicting feature requirements of action classification (demanding temporal invariance) and boundary localization (requiring temporal sensitivity). Existing methods typically adopt decoupled pipelines, unfortunately overlooking the inherent semantic complementarity between these sub-tasks, leading to information silos that prevent beneficial cross-task synergies. To address this challenge, we propose CurvSeg, a novel approach that synergizes classification and localization within the STAS domain through a unique geometric curvature guidance mechanism. Our key innovation lies in exploiting curvature properties of well-learned classification representations on skeleton sequences. Specifically, we observe that high curvature within action segments and low curvature at transitions effectively serve as geometric priors for precise boundary detection. CurvSeg establishes a virtuous cycle: localization predictions, guided by these curvature signals, in turn dynamically refine the classification feature space to organize into a geometry conducive to clearer boundaries. To compute stable curvature signals from potentially noisy skeleton features, we further develop a dual-expert weighting mechanism within a Mixture of Experts framework, providing task-adaptive feature extraction. Comprehensive experiments demonstrate that CurvSeg signif-icantly enhances STAS performance across multiple benchmark datasets, achieving superior results and validating the power of geometric-guided task collaboration for this specific problem.

Optimization · Large Scale, Parallel and Distributed

Rihae Park, Yeonjae Kim, Seung Lee, Yeonhong Park, Jae W. Lee

Dual Modular Redundancy (DMR) is a highly effective mechanism for detecting silent data corruption (SDC)—a critical reliability concern in large language model (LLM) training—by executing each operation twice. However, its high computation overhead has prevented practical deployment at scale. In this paper, we present SpareTrain, an LLM training system that achieves complete DMR with minimal overhead by repurposing the activation checkpointing mechanism and exploiting idle GPU time. Evaluations on up to 32 H200 GPUs show that SpareTrain improves throughput by 12–35\% over naive DMR, corresponding to only 3–14\% overhead compared to unprotected training, while maintaining full DMR error detection capabilities.

Haoyuan Li, Mathias Funk, Aaqib Saeed

Federated Learning (FL) offers a powerful paradigm for training models on decentralized data, but its promise is often undermined by the immense complexity of designing and deploying robust systems. The need to select, combine, and tune strategies for multifaceted challenges like data heterogeneity and system constraints has become a critical bottleneck, resulting in brittle, bespoke solutions. To address this, we introduce Helmsman, a novel LLM-based multi-agent framework that automates the end-to-end synthesis of federated learning systems from high-level user specifications. It emulates a principled research and development workflow through three collaborative phases: (1) interactive human-in-the-loop planning to formulate a sound research plan, (2) modular code generation by supervised generative agent teams, and (3) a closed-loop of autonomous evaluation and refinement in a sandboxed simulation environment. To facilitate rigorous evaluation, we also introduce AgentFL-Bench, a new benchmark comprising 16 diverse tasks designed to assess the system-level generation capabilities of LLM-driven agentic systems in FL. Extensive experiments demonstrate that our approach generates solutions competitive with, and often superior to, established hand-crafted baselines. Our work represents a significant step towards the automated engineering of complex decentralized AI systems. Code is available at: https://github.com/haoyuan-l/Helmsman.

Optimization · Sampling and Optimization

Niels Mündler, Jasper Dekoninck, Martin Vechev

Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a formal language. Yet, due to their probabilistic nature, LLM output is not guaranteed to adhere to such formal languages. To address this, prior work has proposed constrained decoding to restrict LLM generation to particular formal languages. However, existing works are not applicable to the emerging paradigm of diffusion LLMs, as this requires supporting token generation in arbitrary order instead of the traditional left-to-right order. In this paper, we address this challenge and present the first constrained decoding method for diffusion models, one that can handle formal languages captured by context-free grammars. We begin by reducing constrained decoding to the more general additive infilling problem, which asks whether a partial output with holes can be completed to a valid word in the target language. This problem also naturally subsumes the previously unaddressed multi-region infilling constrained decoding. We then reduce this problem to the task of deciding whether the intersection of the target language and a regular language is empty and present an efficient algorithm to solve this task for context-free languages. Empirical results on various applications, such as C++ code infilling and structured data extraction in JSON, demonstrate that our method achieves near-perfect syntactic correctness while consistently preserving or improving functional correctness. Importantly, our efficiency optimizations ensure that the computational overhead remains practical.

General Machine Learning · Probabilistic Methods

Jonas Arruda, Vikas Pandey, Catherine Sherry, Margarida Barroso, Xavier Intes, Jan Hasenauer, Stefan Radev

Amortized Bayesian inference (ABI) with neural networks has emerged as a powerful simulation-based approach for estimating complex mechanistic models. However, extending ABI to hierarchical models, a cornerstone of modern Bayesian analysis, has been a major hurdle due to the need to simulate and process massive datasets. Our study tackles these challenges by extending compositional score matching (CSM), a divide-and-conquer strategy for Bayesian updating using diffusion models. We develop a new error-damping estimator to address previous stability issues of CSM when aggregating large numbers of data points. We first verified the numerical stability with up to 100,000 data points on a controlled benchmark. We then evaluated our method on a hierarchical AR model, achieving competitive performance to direct ABI baselines on smaller problem sizes while using less than one full model simulation for larger problem sizes. Finally, we address a large-scale inverse problem in advanced microscopy with over 750,000 parameters, demonstrating its relevance to real scientific applications.

Computer Vision · Everything Else

Xiaoyang Liu, Zhengyan Zhou, Zihang Xu, Jiezhang Cao, Zheng Chen, Yulun Zhang

Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality image restoration tasks such as deblurring, demonstrating stronger generative capabilities than CNN and transformer-based methods. However, challenges such as unbearable inference time and compromised fidelity still limit the full potential of the diffusion models. To address this, we introduce FideDiff, a novel single-step diffusion model designed for high-fidelity deblurring. We reformulate motion deblurring as a diffusion-like process where each timestep represents a progressively blurred image, and we train a consistency model that aligns all timesteps to the same clean image. By reconstructing training data with matched blur trajectories, the model learns temporal consistency, enabling accurate one-step deblurring. We further enhance model performance by integrating Kernel ControlNet for blur kernel estimation and introducing adaptive timestep prediction. Our model achieves superior performance on full-reference metrics, surpassing previous diffusion-based methods and matching the performance of other state-of-the-art models. FideDiff offers a new direction for applying pre-trained diffusion models to high-fidelity image restoration tasks, establishing a robust baseline for further advancing diffusion models in real-world industrial applications. Our dataset and code will be available at https://github.com/xyLiu339/FideDiff.

Computer Vision · Everything Else

Zheng Chen, Xun Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiongkuo Min, Xiaohong Liu, Xin Yuan, Yong Guo, Yulun Zhang

The development of multimodal large language models (MLLMs) enables the evaluation of image quality through natural language descriptions. This advancement allows for more detailed assessments. However, these MLLM-based IQA methods primarily rely on general contextual descriptions, sometimes limiting fine-grained quality assessment. To address this limitation, we introduce a new image quality assessment (IQA) task paradigm, **grounding-IQA**. This paradigm integrates multimodal referring and grounding with IQA to realize more fine-grained quality perception, thereby extending existing IQA. Specifically, grounding-IQA comprises two subtasks: grounding-IQA-description (GIQA-DES) and visual question answering (GIQA-VQA). GIQA-DES involves detailed descriptions with precise locations (e.g., bounding boxes), while GIQA-VQA focuses on quality QA for local regions. To realize grounding-IQA, we construct a corresponding dataset, GIQA-160K, through our proposed automated annotation pipeline. Furthermore, we develop a well-designed benchmark, GIQA-Bench. The benchmark evaluates the grounding-IQA performance from three perspectives: description quality, VQA accuracy, and grounding precision. Experiments demonstrate that our proposed method facilitates the more fine-grained IQA application. Code: https://github.com/zhengchen1999/Grounding-IQA.

Applications · Chemistry and Drug Discovery

Fang Wu, Stan Z. Li

Protein-protein interaction (PPI) represents a central challenge within the biology field, and accurately predicting the consequences of mutations in this context is crucial for drug design and protein engineering. Deep learning (DL) has shown promise in forecasting the effects of such mutations but is hindered by two primary constraints. First, the structures of mutant proteins are often elusive to acquire. Secondly, PPI takes place dynamically, which is rarely integrated into the DL architecture design. To address these obstacles, we present a novel framework named Refine-PPI with two key enhancements. First, we introduce a structure refinement module trained by a mask mutation modeling (MMM) task on available wild-type structures, which is then transferred to hallucinate the inaccessible mutant structures. Second, we employ a new kind of geometric network, called the probability density cloud network (PDC-Net), to capture 3D dynamic variations and encode the atomic uncertainty associated with PPI. Comprehensive experiments on SKEMPI.v2 substantiate the superiority of Refine-PPI over all existing tools for predicting free energy change. These findings underscore the effectiveness of our hallucination strategy and the PDC module in addressing the absence of mutant protein structure and modeling geometric uncertainty.

Social Aspects · Accountability, Transparency and Interpretability

Sara Kangaslahti, Elan Rosenfeld, Naomi Saphra

Loss curves are smooth during most of model training, so visible discontinuities stand out as possible conceptual breakthroughs. Studying these breakthroughs enables a deeper understanding of learning dynamics, but only when they are properly identified. This paper argues that similar breakthroughs occur frequently throughout training but they are obscured by a loss metric that collapses all variation into a single scalar. To find these hidden transitions, we introduce POLCA, a method for decomposing changes in loss along arbitrary bases of the low-rank training subspace. We use our method to identify clusters of samples that share similar changes in loss during training, disaggregating the overall loss into that of smaller groups of conceptually similar data. We validate our method on synthetic arithmetic and natural language tasks, showing that POLCA recovers clusters that represent interpretable breakthroughs in the model's capabilities. We demonstrate the promise of these hidden phase transitions as a tool for unsupervised interpretability.

Computer Vision · Vision Models & Multimodal

Balamurugan Thambiraja, Omid Taheri, Radek Danecek, Giorgio Becherini, Gerard Pons-Moll, Justus Thies

Hands play a central role in daily life, yet modeling natural hand motions remains underexplored. Existing methods that tackle text-to-hand-motion generation or hand animation captioning rely on studio-captured datasets with limited actions and contexts, making them costly to scale to “in-the-wild” settings. Further, contemporary models and their training schemes struggle to capture animation fidelity with text–motion alignment. To address this, we (1) introduce ‘3D Hands in the Wild’ (3D-HIW), a dataset of 32K 3D hand-motion sequences and aligned text, and (2) propose CLUTCH, an LLM-based hand animation system with two critical innovations: (a) SHIFT, a novel VQ-VAE architecture to tokenize hand motion, and (b) a geometric refinement stage to finetune the LLM. To build 3D- HIW, we propose a data annotation pipeline that combines vision–language models (VLMs) and state-of-the-art 3D hand trackers, and apply it to a large corpus of egocentric action videos covering a wide range of scenarios. To fully capture motion in-the-wild, CLUTCH employs SHIFT, a part–modality decomposed VQ- VAE, which improves generalization and reconstruction fidelity. Finally, to improve animation quality, we introduce a geometric refinement stage, where CLUTCH is co-supervised with a reconstruction loss applied directly to decoded hand motion parameters. Experiments demonstrate state-of-the-art performance on text-to- motion and motion-to-text tasks, establishing the first benchmark for scalable in-the-wild hand motion modelling. Code, data and models will be released.

General Machine Learning · Transfer, Multitask and Meta-learning

Hengyu Luo, Raúl Vázquez, Timothee Mickus, Filip Ginter, Jörg Tiedemann

Concerns have been raised that knowledge distillation may transfer test-set knowledge from a contaminated teacher to a clean student---a "data laundering" effect that potentially threatens evaluation integrity. In this paper, we assess the severity of this phenomenon. If these concerns regarding data laundering are minor, then distillation could be used to mitigate risks of direct data exposure. Across eight classification benchmarks, we find that substantial laundering is the exception rather than the rule: unlike the large performance gains from direct contamination, any accuracy inflation from laundering is consistently smaller and statistically insignificant in all but two cases. More broadly, using sample-level analysis, we find that the two phenomena are weakly correlated, suggesting that laundering is not simply a diluted form of contamination but a distinct effect that arises primarily when benchmarks exhibit large train–test distribution gaps. Motivated by this, we conduct controlled experiments that systematically enlarge the train–test distance on two benchmarks where laundering was initially negligible, and observe that laundering becomes more significant as the gap widens. Taken together, our results indicate that knowledge distillation, despite rare benchmark-specific residues, can be expected to function as an effective decontamination technique that largely mitigates test-data leakage.

Deep Learning · Generative Models and Autoencoders

Jiajia Yu, Junghwan Lee, Yao Xie, Xiuyuan Cheng

Mean-field games (MFGs) study the Nash equilibrium of systems with a continuum of interacting agents, which can be formulated as the fixed-point of optimal control problems. They provide a unified framework for a variety of problems, including both potential and non-potential games, with applications in areas such as generative modeling. Despite their broad applicability, solving high-dimensional MFGs remains a significant challenge due to fundamental computational and analytical obstacles. In this work, we propose a particle-based deep Flow Matching (FM) method to tackle high-dimensional MFG computation. In each iteration of our proximal fixed-point scheme, particles are updated using first-order information, and a flow neural network is trained to match the velocity of the sample trajectories. Theoretically, in the optimal control setting, we prove that our scheme converges to a stationary point sublinearly, and upgrade to linear (exponential) convergence under additional convexity assumptions. Our proof uses FM to induce an Eulerian coordinate (density-based) from a Lagrangian one (particle-based), and this also leads to certain equivalence results between the two formulations for MFGs when the Eulerian solution is sufficiently regular. Our method demonstrates promising experimental performance on MFGs in high dimensions.

Computer Vision · Vision Models & Multimodal

Jiuming Liu, Mengmeng Liu, Siting Zhu, Yunpeng Zhang, Jiangtao Li, Michael Yang, Francesco Nex, Hao Cheng, Hesheng Wang

Optical flow estimation is a fundamental computer vision task that predicts per-pixel displacements from consecutive images. Recent works attempt to exploit temporal cues to improve the estimation performance. However, their temporal modeling is restricted to short video sequences due to the unaffordable computational burden, thereby suffering from restricted temporal receptive fields. Moreover, their group-wise paradigm in one forward pass undermines inter-group information exchange, leading to modest performance improvement. To address these problems, we propose a novel multi-frame optical flow network based on an auto-regressive paradigm, named ARFlow. Unlike previous multi-frame methods, our method can be scalable to arbitrary-length videos with marginal computational overhead. Specifically, we design an Auto-regressive Flow Initialization (AFI) module and an Auto-regressive Multi-stride Flow Refinement (AMFR) module to forecast the next-frame flow based on multi-stride history observations. Our ARFlow achieves state-of-the-art performance, ranking 1st on both KITTI-2015 and Spring official benchmarks and 2nd on the MPI-Sintel (Final) benchmark among all open-sourced methods. Furthermore, due to the auto-regressive nature, our method can generalize to arbitrary video length with a constant GPU memory usage of 2.1GB.

Applications · Language, Speech and Dialog

Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch

Long document summarization remains a significant challenge for current large language models (LLMs), as existing approaches commonly struggle with information loss, factual inconsistencies, and coherence issues when processing excessively long documents. We propose SummQ, a novel adversarial multi-agent framework that addresses these limitations through collaborative intelligence between specialized agents operating in two complementary domains: summarization and quizzing. Our approach employs summary generators and reviewers that work collaboratively to create and evaluate comprehensive summaries, while quiz generators and reviewers create comprehension questions that serve as continuous quality checks for the summarization process. This adversarial dynamic, enhanced by an examinee agent that validates whether the generated summary contains the information needed to answer the quiz questions, enables iterative refinement through multifaceted feedback mechanisms. We evaluate SummQ on three widely used long document summarization benchmarks. Experimental results demonstrate that our framework significantly outperforms existing state-of-the-art methods across ROUGE and BERTScore metrics, as well as in LLM-as-a-Judge and human evaluations. Our comprehensive analyses reveal the effectiveness of the multi-agent collaboration dynamics, the influence of different agent configurations, and the impact of the quizzing mechanism. This work establishes a new approach for long document summarization that uses adversarial agentic collaboration to improve summarization quality.