论文检索

Probabilistic Methods · Bayesian Models and Methods

Dongqing Li, Zheqiao Cheng, Geoff Nicholls, Quyu Kong

AI agents increasingly execute procedural workflows as sequential action traces, which obscures latent concurrency and induces repeated step-by-step reasoning. We introduce BPOP, a Bayesian framework that infers a latent dependency partial order from noisy linearized traces. BPOP models traces as stochastic linear extensions of an underlying graph and performs efficient MCMC inference via a tractable frontier-softmax likelihood that avoids \#P-hard marginalization over linear extensions. We evaluate on our open-sourced Cloud-IaC-6, a suite of cloud provisioning tasks with heterogeneous LLM-generated traces, and WFCommons scientific workflows. BPOP recovers dependency structure more accurately than trace-only and process-mining baselines, and the inferred graphs support a compiled executor that prunes irrelevant context, yielding substantial reductions in token usage and execution time.

Deep Learning · Large Language Models

Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su 等

The reasoning patterns of large language models (LLMs) remain opaque, and Reinforcement learning (RL) typically assigns uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work treats attention as a natural substrate for interpreting LLM reasoning and a window for aligning optimization with its internal dynamics. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We quantify these with two metrics measuring the extent of backward attention within a clipped window and the average attention a token receives from subsequent tokens, respectively. Taken together, these signals reveal a recurring preplan-and-anchor mechanism, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks.

Deep Learning · Large Language Models

GuanHao Zhao, Wenbo Lu, Cheng Cheng, Zhenya Huang, Wei Song, Zhiding Liu, Runze Wu, Enhong Chen

The collective intelligence of Large Language Model (LLM)-based Multi-Agent Systems (MAS) is fundamentally governed by the underlying communication graph. However, discovering task-adaptive structures within this combinatorial search space remains a significant challenge. Existing methods, ranging from heuristic pruning to autoregressive generation, often lack a unified theoretical framework to guide the self-organization of agents into efficient teams. In this paper, we bridge non-equilibrium thermodynamics and generative modeling to formalize multi-agent graph generation as an energy minimization process. Specifically, we frame the emergence of efficient collaboration as a thermodynamic "cooling" process, where initially stochastic interactions converge to a low-energy, structured equilibrium. To implement this, We propose MAGE (Multi-Agent Communication Graph Generation), a score-based diffusion framework that constructs communication graphs by navigating the energy landscape via iterative denoising and first-order gradient guidance. Extensive experiments on representative benchmarks demonstrate that MAGE achieves state-of-the-art performance. Furthermore, qualitative analysis reveals that the generated graphs mirroring the functional specialization of human organizations, validating our thermodynamic hypothesis.

Deep Learning · Large Language Models

Yuxuan Li, Lingxi Xie, Xinyue Huo, Jihao Qiu, Jiacheng Shao, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Qi Tian

Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on **speaker recognition**, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce **DramaSR-532K**, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose **DramaSR-LRM**, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short utterances where acoustic biometrics are inherently unreliable. *All the data and code will be made publicly available.*

Deep Learning · Sequential Models, Time series

Yanbo Li, Richard Cornelius Suwandi, Feng Yin, Yiyong SUN, Wei Huang, Wenqiang Pu

The state space duality (SSD) framework, central to modern state-space models (SSMs) such as Mamba, has established an efficient attention-like mechanism by leveraging the commutative property of linear recurrences. However, existing formulations are limited to single-input single-output (SISO) systems that enforce commutativity with a restrictive scalar-identity constraint, which prevents cross-dimensional interactions within the state dynamics. In this work, we generalize SSD to the multi-input multi-output (MIMO) setting by introducing a matrix polynomial parameterization. This approach not only provides a principled way to ensure commutativity for generalized duality but also induces a shared algebraic structure across state transitions, thereby significantly reducing parameter redundancy. Building on this foundation, we present \textbf{MIMOMamba}, a multi-head SSM architecture that captures rich cross-dimensional dynamics while retaining linear-time training. Empirical results on a sequence modeling benchmark show that MIMOMamba matches or exceeds the performance of standard Transformers with only approximately one-third the parameters of the baseline.

Deep Learning · Large Language Models

Subbarao Kambhampati, Karthik Valmeekam, Siddhant Bhambri, Vardhan Palod, Lucas Saldyt, Kaya Stechly, Soumya Samineni, Durgesh Kalwar, Upasana Biswas

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thoughts} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.

Applications · Robotics

Dong Jing, Gang Wang, Jiaqi Liu, Weiliang Tang, Zelong Sun, Yunchao Yao, Zhenyu Wei, Yunhui Liu, Zhiwu Lu, Mingyu Ding

Vision-language-action models exhibit an inherent trade-off in action chunk length (``horizon''): longer horizons improve global foresight but degrade fine-grained local control, while shorter ones yield the opposite. To mitigate the trade-off, we propose a $\textbf{mixture of horizons (MoH)}$ strategy. In brief, MoH rearranges the action chunk into several segments with different horizons, processes them in parallel with a shared action transformer, and fuses outputs with a light linear gate. It offers three appealing benefits. i) Long-term foresight and short-term precision are jointly exploited within a single model. ii) MoH is plug-and-play for full-attention action modules with minimal training or inference overhead. iii) MoH enables dynamic inference with adaptive horizons, which selects stable actions through cross-horizon consensus, achieving 2.5$\times$ higher throughput than baselines while preserving superior performance. Extensive experiments over flow-based and one-step regression policies demonstrate that MoH yields consistent and significant gains on both simulations and real-world tasks. Notably, under mixed-task setting, $\pi_{0.5}$ with MoH reaches a new state-of-the-art with 99\% average success rate on LIBERO after only $30k$ training iterations.

Deep Learning · Attention Mechanisms

Peter Racioppo

We introduce Robust Filter Attention (RFA), an attention mechanism that reformulates self-attention as parallel robust filtering under a latent stochastic differential equation (SDE) prior, where analytically propagated uncertainty defines a time-dependent precision prior over attention weights. This formulation integrates key advantages of existing positional encodings: it preserves RoPE-style rotational structure while achieving long-context stability through explicit modeling of dissipation and diffusion. By imposing isotropic constraints on the dynamics and noise, RFA matches the $\mathcal{O}(N^2 d)$ time and $\mathcal{O}(N^2 + Nd)$ memory complexity of standard attention. Empirically, we find that uncertainty-aware weighting induces specialization into distinct filtering regimes across heads, improving temporal consistency and extrapolation across varying context lengths.

Deep Learning · Graph Neural Networks

Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos

Representation learning is central to graph machine learning, powering tasks such as link prediction and node classification. However, most graph embeddings are hard to interpret, offering limited insight into how learned features relate to graph structure. Many networks naturally admit a role-mixture view, where nodes are best described as mixtures over latent archetypal factors. Motivated by this structure, we propose a compositional graph embedding framework grounded in Aitchison geometry, the canonical geometry for comparing mixtures. Nodes are represented as simplex-valued compositions and embedded via isometric log-ratio (ILR) coordinates, which preserve Aitchison distances while enabling unconstrained optimization in Euclidean space. This yields intrinsically interpretable embeddings whose geometry reflects relative trade-offs among archetypes and supports coherent behavior under component restriction; we consider both fixed and learnable ILR bases. Across node classification and link prediction, our method achieves competitive performance with strong baselines while providing explainability by construction rather than post hoc. Finally, subcompositional coherence enables principled component restriction: removing and renormalizing subsets preserves a well-defined geometry, which we exploit via subcompositional dimensionality removal to probe how archetype groups influence representations and predictions.

Tian-Shuo Liu, Chengxing Jia, Haoyu Liu, Pengyuan Wang, Shiyuan Zhang, Jie Fu, Yang Yu

Supervised Fine-Tuning (SFT) is a critical step for adapting Large Language Models (LLMs) to specialized domains, often serving as an initialization for subsequent reinforcement learning (RL). However, SFT can overfit a small set of expert data, harming generalization and eroding prior knowledge. This can limit downstream RL, which benefits from a strong, generalizable initialization for exploration. Here, we demonstrate that prior knowledge degradation primarily results from tokens in the expert data to which the base model assigns low probability. Specifically, these low-probability tokens represent a significant deviation from the model’s current prior knowledge. Due to the nature of the log-likelihood objective, they produce larger gradient magnitudes, which speed up adaptation to the new data but degrade generalization. In this paper, we study the token-wise clipping strategy, a commonly used trust-region method for bounding per-token updates. We find that it reshapes token-level learning priorities, promoting more progressive adaptation that fits the new data while preserving general abilities. Compared with standard SFT, clipping low-probability tokens reduces out-of-distribution forgetting by 11.54\% and improves final RL performance by 7.09\% across the agentic benchmarks. Moreover, latent-space analysis shows smaller representational drift under clipping, indicating that it provides a generalizable initialization.

Applications · Computer Vision

Ye Wang, Maocai Dai, Jiang Xie, Xiuli Bi, Fei Tao, Xiao Li, Hong Yu

Image Aesthetic Assessment (IAA) predicts an image’s overall aesthetic score, yet aesthetic is influenced by multiple attributes whose relative importance varies with image content and usage scenarios. Under end-to-end training with only overall-score supervision, attribute signals are blended, which can cause gradient conflict across samples dominated by different attributes, resulting in gradient cancellation and persistent systematic bias. To address these issues, we propose AGREE (Attribute-guided Gradient Routing for Establishing Agreement), which learns attribute-specific subspaces and performs gradient routing based on sample-wise attribute sensitivity estimated via perturbation analysis. AGREE further reduces feature coupling across attributes with semantic anchors and improves robustness via error-aware reweighting. Experiments on AVA, LAPIS, AADB, TAD66K, and PARA show consistent improvements over diverse IAA baseline models, and AGREE is plug-and-play for existing end-to-end IAA methods without modifying their original architectures. To our knowledge, this work is among the early efforts in IAA to systematically study gradient conflict and provide an effective solution.

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on chart reasoning, geometric problem solving, and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the Qwen-VL base model.

General Machine Learning · Representation Learning

Jiarong Yang, Yuan Liu

Adopting pre-trained Vision-Language Models (VLMs) in Federated Learning (FL) presents a promising avenue for mitigating data scarcity and heterogeneity. However, existing solutions suffer from high computational complexity or ineffective knowledge aggregation. To address these problems, we propose FedSPA (Federated Adaptation via Semantic-Visual Prototype Alignment). On the client side, FedSPA restricts local optimization to visual prototypes, enabling lightweight personalization. On the server side, we introduce a semantic alignment module that leverages client-uploaded prototypes to minimize a contrastive objective, aligning global semantic prototypes with heterogeneous visual distributions and thereby shifting the paradigm from traditional “learning-to-describe" (optimizing static prompts) to ”learning-to-align". Extensive experiments demonstrate that FedSPA significantly outperforms state-of-the-art methods in both personalized and global benchmarks, while substantially reducing computational overhead.

Deep Learning · Large Language Models

Jiaxi Liu, Yanzuo Jiang, Guibin Zhang, Zihan Zhang, Heng Chang, Zhenfei Yin, Qibing Ren, Junchi Yan

Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to the structural diversity of open-ended problems. To address this limitation, we introduce TodoEvolve, a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning architectures. Specifically, we first construct PlanFactory, a modular design space that standardizes diverse planning paradigms within a unified codebase encompassing topology, initialization, adaptation, and navigation, thereby providing a common interface for heterogeneous planning patterns. Leveraging PlanFactory, we collect high-quality planning trajectories and train Todo-14B via \textit{Impedance-Guided Preference Optimization} (IGPO), a multi-objective reinforcement learning objective that encourages the generation of planning systems that are performant, stable, and token-efficient across arbitrary tasks and agent backbones. Empirical evaluations on five agentic benchmarks demonstrate that TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.

Deep Learning · Large Language Models

Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi, Ola Svensson

Retrieval-augmented generation (RAG) systems typically rely on a single retriever and a single set of hyperparameters, despite facing highly heterogeneous queries that range from simple factoid questions to complex multi-hop reasoning. We propose a method that automatically selects a small, diverse subset of retrievers--a portfolio--from a large pool of candidates, to cover different regions of the target query distribution. We formalize this setting via an expected best-of-$k$ objective over the query distribution and show that it admits an efficient portfolio construction algorithm with near-optimal guarantees. Across multiple QA benchmarks, our learned portfolios and router pipeline consistently outperform single-retriever and naive multi-retriever baselines on both retrieval metrics and answer quality. In addition, compared to inference-time hyperparameter tuning approaches, fixed portfolios enable parallel retrieval and LLM calls, achieving comparable (and sometimes better) accuracy with substantially lower latency and token cost.

Applications · Chemistry, Physics, and Earth Sciences

Nima Leclerc, Chris Miller, Nicholas Brawand

Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales linearly with task variance, providing a quantitative criterion for when adaptation justifies its overhead. Validation on quantum gate calibration shows negligible benefits for low-variance tasks but $>40$% fidelity gains on two-qubit gates under extreme out-of-distribution conditions (10$\times$ the training noise), with implications for reducing per-device calibration time on cloud quantum processors. Further validation on classical linear-quadratic control confirms these laws emerge from general optimization geometry rather than quantum-specific physics. Together, these results offer a transferable framework for decision-making in adaptive control.

Shikun Sun, Shuo Huang, Yiding Chen, Wen Sun, Jia Jia

Reinforcement learning with diffusion models has shown strong potential, but existing approaches such as variants of Direct Preference Optimization (DPO) often rely on an inaccurate simplification: they equate trajectory likelihoods with final-state probabilities. This mismatch leads to suboptimal alignment. We address this limitation with a principled framework that leverages the optimal value function as the return for short trajectory segments. Our approach follows a two-stage procedure: (i) learning a value-distribution function to estimate segment-level returns, and (ii) applying our VRPO to refine the score function. We prove that, under sufficient model capacity, the resulting model is equivalent to training a diffusion process on the tilted distribution proportional to $p(x)\exp(\eta r(x))$. Experiments on large-scale diffusion models validate our analysis and show stable and consistent improvements over prior methods.

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on chart reasoning, geometric problem solving, and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the Qwen-VL base model.

Deep Learning · Large Language Models

Jiaqi Liu, Yaofeng Su, Peng Xia, Siwei Han, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which distills unstructured interactions into compact, multi-view indexed memory units; (2) Online Semantic Synthesis, an intra-session process that instantly integrates related context into unified abstract representations to eliminate redundancy; and (3) Intent-Aware Retrieval Planning, which infers search intent to dynamically determine retrieval scope and construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% in LoCoMo while reducing inference-time token consumption by up to 30×, demonstrating a superior balance between performance and efficiency.

Jiayi Luo, Jiayu Chen, Jiankun Wang, Cong Wang, Hanxin Zhu, Qingyun Sun, Chen Gao, Zhibo Chen, Jianxin Li

Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, leading to the development of sparse attention technologies to improve efficiency. However, existing training-free sparse attention methods in video generation still face two unresolved limitations: *ignoring layer heterogeneity in attention pruning* and *ignoring query-key coupling in block partitioning*, which hinder a better quality-speedup trade-off. In this work, we uncover a critical insight that **the attention sparsity of each layer is its intrinsic property, with minor effects across different inputs**. Motivated by this, we propose **SVOO**, a training-free **S**parse attention framework for fast **V**ideo generation via **O**ffline layer-wise sparsity profiling and **O**nline bidirectional co-clustering. Specifically, SVOO adopts a two-stage paradigm: (i) offline layer-wise sensitivity profiling to derive intrinsic per-layer pruning levels, and (ii) online block-wise sparse attention via a novel bidirectional co-clustering algorithm. Extensive experiments on seven widely used video generation models demonstrate that SVOO achieves a superior quality-speedup trade-off over state-of-the-art methods, delivering up to 1.93× speedup while maintaining a PSNR of up to 29 dB on Wan2.1.