论文检索

Reinforcement Learning · Multi-agent

Haolun MA, Yanchen ZHU, Zizhuo Xu, Weijie Shi, Jiajie Xu, Lei Li

Learning-based Traffic Signal Control (TSC) achieves satisfactory performance in small networks, but its effectiveness often deteriorates in larger networks under dynamic traffic patterns and intersection heterogeneity. In this work, we propose SLight, a policy-aware grouped MARL-TSC framework that enables scalability and efficiency balance under dynamic and heterogeneous traffic conditions. SLight captures policy-influenced traffic patterns with a policy-aware traffic pattern encoder, learns explicit group-level shared control principles from state–action trajectories, and matches each intersection’s traffic pattern embedding to principle prototypes flexibly through a compatibility-based adaptive assignment module. Experiments on real-world and synthetic networks demonstrate that SLight sustains performance gains as scale increases and outperforms existing rule-based, reinforcement learning, and grouping-based baselines. Code is available at \url{https://anonymous.4open.science/r/code-20D3/}

Social Aspects · Accountability, Transparency, and Interpretability

Siddharth Boppana, Annabel Ma, Max Loeffler, Raphaël Sarfati, Eric Bigelow, Atticus Geiger, Jack Merullo, Owen Lewis

Do the chains of thought (CoT) of reasoning Large Language Models (LLMs) reflect their internal computation? In this paper, we provide evidence of \textit{performative} CoT, where a model becomes strongly confident in its final answer, but continues generating excess tokens without revealing its internal belief. Our analysis compares activation probing of the model's final answer and early forced answering to a CoT monitor across two large reasoning models (DeepSeek-R1 671B \& GPT-OSS 120B). We observe difficulty-specific differences for these methods: the gap between the expressed CoT and the model's internal belief is larger for MMLU-Redux questions that are easier and recall-based, and is smaller on more difficult multihop GPQA-Diamond questions. We also study certain inflection points within individual reasoning traces, finding that they correspond to updates in probe confidence. Finally, we leverage our probes to enable confidence-based early exit from CoT that saves up to 80\% of tokens on MMLU and 30\% of tokens on GPQA while maintaining similar accuracy. This work provides nuance to discussions on CoT faithfulness, and establishes attention probing as an efficient method for detecting performative reasoning and for adaptive computation in reasoning LLMs.

Social Aspects · Accountability, Transparency, and Interpretability

Joshua Tan, Nicholas Vincent, Katherine Elkins, Magnus Sahlgren, Joseph Low, David Pham, Sampo Pyysalo, Jenia Jitsev

Open source projects have made incredible progress in producing widely usable machine learning models and systems, but open source alone will face challenges in fully democratizing access to AI. Unlike previous generations of open source software, open source and open weight AI models require substantial resources to activate and maintain—e.g., data and compute for pre-training, post-training, and deployment—which only a few actors can currently provide. This position paper argues that open source AI must be complemented by public AI: infrastructure and institutions that ensure models are accessible, sustainable, and governed in the public interest. To achieve the full promise of AI models as prosocial public goods, we need to build public infrastructure to power and deliver open source software and models.

Probabilistic Methods · Monte Carlo and Sampling Methods

Emanuel Sommer, David Rügamer

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at the verge of superseding such methods for effective and efficient inference in BNNs. This development should be in the interest of the whole community, promoting BNNs as a principled paradigm with its long-standing yet unfulfilled promise of providing principled uncertainty quantification for neural networks. SAI can even do more—yielding superior prediction performance through model averaging, serving as the foundation for a plethora of possible downstream tasks, and providing crucial insights into the landscape of BNNs. In order to make such a change happen and unfold the potential of sampling, overcoming current misconceptions is a necessary first step. The next step is to realign research efforts toward addressing remaining challenges in SAI. In particular, the community must focus on two core problems: sufficient exploration of the posterior landscape and high-fidelity distillation of posterior samples for efficient downstream inference. By addressing conceptual and practical obstacles, we can unlock the full potential of SAI and establish it as a central tool in Bayesian deep learning.

Deep Learning · Large Language Models

Beibei Xiong, Hangyu Lv, Junqi Liu, Yisen Wang, Shaoshi Chen, Jianlin Wang, Zhengfeng Yang, Lihong Zhi

Automating formal proofs of combinatorial identities is challenging for LLM-based provers, as long-horizon proof planning is required and unconstrained search quickly explodes. Symbolic methods such as the Wilf--Zeilberger (WZ) method can achieve a mechanized proof of combinatorial identities by constructing special auxiliary functions and demonstrating that they satisfy specific recurrence relations. We propose WZ-LLM, a neuro-symbolic framework that turns WZ proof plans into executable proof sketches in Lean~4 and uses an LLM-based prover to discharge the resulting machine-checkable subgoals. We also train a dedicated WZ-Prover via a Lean-kernel-verified bootstrapping loop with expert-verified iteration, followed by DAPO-based refinement. Experiments show that WZ-LLM achieves a 34\% proof success rate on LCI-Test (100 classical combinatorial identities), outperforming strong baselines such as DeepSeek-V3 and Goedel-Prover-V2; moreover, on LCI-Test it proves 5 identities on which the symbolic-only baseline fails. WZ-LLM also improves performance on CombiBench and PutnamBench-Comb, suggesting the effectiveness of coupling symbolic proof sketches with learned formal reasoning. Experiments show that WZ-LLM achieves a 34\% proof success rate on LCI-Test (100 classic combinatorial identities), outperforming strong baselines such as DeepSeek-V3 and Goedel-Prover-V2, and delivering consistent gains on CombiBench and PutnamBench-Comb. These results indicate that our framework provides two complementary strengths: improved direct proving for identities beyond the scope of WZ, and substantially higher end-to-end success when WZ sketches guide a specialized prover.

Zeyao Ma, Jing Zhang, Xiaokang Zhang, Jiaxi Yang, Zongmeng Zhang, Jiajun Zhang, Yuheng Jing, Lei Zhang, Hao Zheng, Wenting Zhao 等

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling. To address this limitation, we propose **Agentic Verifier**, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs that expose behavioral discrepancies among candidate solutions. Through multi-turn interaction with code execution environments, the verifier iteratively refines the candidate input generator and produces targeted counterexamples rather than blindly sampling inputs. We train the verifier to acquire this discriminative input generation capability via a scalable pipeline combining large-scale data synthesis, rejection fine-tuning, and agentic reinforcement learning. Extensive experiments across five competitive programming benchmarks demonstrate consistent improvements over strong execution-based baselines, achieving up to **+10-15\%** absolute gains in Best@$k$ accuracy. Further analysis reveals clear test-time scaling behavior and highlights the verifier’s broader potential beyond reranking.

Applications · Chemistry, Physics, and Earth Sciences

Zemin Xu, Chenyu Wu, Wenbo Xie, Peijun Hu

Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs), and it remains unclear whether it is the only practical design principle, or whether irreducible Cartesian tensors (ICTs) can offer distinct advantages by operating directly in the Cartesian space that naturally aligned with atomistic coordinates and tensor targets. In this work, we introduce the Cartesian-3j and Cartesian-nj symbols, which serve as direct analogues of the Wigner-3j and Wigner-nj symbols defined for spherical tensor coupling. We further extend the e3nn library to support ICT products, and use this framework to build Cartesian counterparts of MACE, NequIP, and Allegro, allowing the first controlled comparison where architectures are held fixed and only the tensor basis is changed. Leveraging the ICTs and Cartesian-based architecture, a universal interatomic potential is trained and demonstrated competitive performance on a widely used public benchmark for materials discovery against SOTA ST models.

Applications · Computer Vision

Huangbiao Xu, huanqi wu, Xiao Ke, Yuxin Peng

Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availability during training to provide reconstruction supervision or cross-modal priors. This paper tackles the more challenging setting of IML under training-time incomplete observations, which precludes reliance on a "God's eye view" of complete data. We propose LIMSSR (LLM-Driven Incomplete Multimodal Sequence-to-Score Reasoning), a framework that reformulates this challenge as a conditional sequence reasoning task. LIMSSR leverages the semantic reasoning capabilities of Large Language Models via Prompt-Guided Context-Aware Modality Imputation and Multidimensional Representation Fusion to infer latent semantics from available contexts without direct reconstruction. To mitigate hallucinations, we introduce a Mask-Aware Dual-Path Aggregation to dynamically calibrate inference uncertainty. Extensive experiments on three Action Quality Assessment datasets demonstrate that LIMSSR significantly outperforms state-of-the-art baselines without relying on complete training data, establishing a new paradigm for data-efficient multimodal learning. Code will be released upon acceptance.

Applications · Health / Medicine

Shiva Kaul, Anjum Khurshid

Medical AI has rapidly improved its ability to perform diagnostic and prognostic tasks that lead to treatment decisions. But understanding of treatment itself is still inadequately trained and evaluated, using human opinions and syntheses (especially texts such as biomedical publications and clinical practice guidelines) rather than actual underlying data on treatment outcomes. This neglect seriously limits the long-term potential of medical AI, and is already causing deficiencies in both frontier models and major benchmarks, as argued in this position paper. Real treatment outcomes, drawn from sources such as observational databases and randomized experiments, should be substantially incorporated into both training and evaluation. Improving these outcomes should be reemphasized as the goal of all medical AI.

General Machine Learning · Evaluation

Fredrik Carlsson, Dan Ward, Joseph Ortiz, Fangyu Liu, Joakim Nivre

As the reasoning capabilities of Large Language Models (LLMs) expand, evaluating true inductive generalization on entirely unseen data becomes increasingly challenging. To this end, we introduce a modular in-context learning evaluation framework, that is scalable and extendable across its separate modules. This is based upon the notion of synthetic scenarios with controllable complexity across three independent axes: \\ \textbf{1)} the logic of the underlying data distribution (UDD) \textbf{2)} their projection into diverse representations, and \textbf{3)} the interaction dynamic determining how the model accesses and explores the data. For these scenarios, the model is tasked to perform in-context scientific discovery and produce an interpretable theory in natural language that explains the observations. In a separate conversation, the model is then tasked to convert this generated theory into executable code, which can be programmatically compared against the underlying data distribution. Using this modular framework we produce an initial suite of 600 diverse scenarios that we use to evaluate and analyze various state-of-the-art LLMs. Although these experiments show that Gemini 3.0 Pro achieves the best overall score, each model performs the best at different tasks. For example: GPT 5.2 is the clear winner on pure symbolic data, Claude Opus 4.5 is the best at working with files, Gemini is the strongest model for the non-dynamic scenarios, and Grok 4.1 is the strongest model when UDD complexity scales. Furthermore, all models struggle with active exploration and are seemingly incapable of identifying informative data points, resulting in less efficient exploration than a random baseline. This highlights the room for improvement state-of-the-art LLMs have, even without further scaling of the complexity of the benchmark.

Applications · Computer Vision

Lancheng Gao, Ziheng Jia, Zixuan Xing, Wei Sun, Huiyu Duan, Guangtao Zhai, Xiongkuo Min

Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce **EEmoDB**, the largest image-evoked emotion understanding dataset to date. It features $5$ analysis dimensions spanning $5$ distinct task categories, facilitating comprehensive interpretation. Specifically, we compile $1.2M$ question-answering (QA) pairs (EEmoDB-QA) from $125k$ images via automated generation, alongside a $36k$ dataset (EEmoDB-Assess) curated from $25k$ images for fine-grained assessment. Furthermore, we propose **EEmo-Logic**, an **all-in-one** multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The code is available at [https://anonymous.4open.science/r/EEmoLogic](https://anonymous.4open.science/r/EEmoLogic).

Optimization · Stochastic

Vassilis Apidopoulos, Iosif Lytras, Panayotis Mertikopoulos

Many optimization problems in machine learning and data science—from deep neural networks to Bayesian inference and beyond—fall outside the standard Lipschitz smoothness framework that underpins the convergence theory of stochastic gradient descent (SGD). Motivated by this theory-practice disconnect, we examine the almost sure convergence of the trajectories of SGD in non-convex landscapes under a generalized $(L_0,L)1)$-smoothness condition which allows for gradients with superlinear growth (even exponential). We begin by proposing a taming scheme for SGD that achieves almost sure convergence under a generalized ABC-type condition on the gradient noise. Subsequently, to relax this requirement, we introduce a more flexible, dissipative taming scheme which converges almost surely under less restrictive moment bound conditions for the stochastic gradients entering the process. For both taming schemes, we show that the generated trajectories avoid strict saddle points (and/or manifolds thereof) with probability 1 so, generically, both methods only converge to local minimizers.

Deep Learning · Large Language Models

Haobo Lin, Tianyi Bai, Chen Chen, Jiajun Zhang, Bohan Zeng, Wentao Zhang, Binhang Yuan

Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data and weak visual--symbolic alignment. We propose a pipeline for synthesizing complex multimodal geometry problems from scratch and construct a dataset named \textbf{GeoCode}, which decouples problem generation into symbolic seed construction, grounded instantiation with verification, and code-based diagram rendering, ensuring consistency across structure, text, reasoning, and images. Leveraging the plotting code provided in GeoCode, we further introduce code prediction as an explicit alignment objective, transforming visual understanding into a supervised structured prediction task. GeoCode exhibits substantially higher structural complexity and reasoning difficulty than existing benchmarks, while maintaining mathematical correctness through multi-stage validation. Extensive experiments show that models trained on GeoCode achieve consistent improvements on multiple geometry benchmarks, demonstrating both the effectiveness of the dataset and the proposed alignment strategy. The code is available at \url{https://anonymous.4open.science/r/SGD-Z368/}.

Social Aspects · Safety

Mansur Ali Khan, Mehmet Efe Akengin, Osman Salahuddin, Ahmad A. Rushdi

While AI models advance at unprecedented rates, AI safety legislation in the United States remains largely stalled or unrealized. We observe that AI policy activity is increasing globally, yet binding enactments remain limited relative to the pace of technical capability releases. We argue for the need to bridge this gap between AI development and its regulation. Specifically, we support our position through a technical analysis of all U.S. AI-related bills introduced from 2017 to 2025, showing that only 4.23% of U.S. AI bills reach any terminal outcome. We identify that procedural bottlenecks, including committee pigeonholing, multi-sponsor coordination challenges, and expertise asymmetries, are primary correlates of legislative stalling. Our comprehensive analysis of institutional, economic, political, and informational constraints shows factors exacerbating these regulatory delays. To address this multi-faceted gap, we propose policy recommendations grounded in planned adaptation, preemptive enactment, and independent AI oversight. Finally, we highlight the need for coordinated action across policymakers, developers, and industry stakeholders so that AI safety governance keeps pace with technological innovation.

Optimization · Stochastic

Wei Jiang, Mao Xu, Wenhao Yang, Yibo Wang, Zechao Li, Lijun Zhang

In this paper, we provide a comprehensive convergence analysis for the Lion optimizer. First, we establish that the original Lion achieves a convergence rate of $\mathcal{O}(d^{1/2}T^{-1/4})$, where $d$ denotes the problem dimension and $T$ is the iteration number. To improve this rate, we propose a variance reduction variant of Lion, which attains an enhanced rate of $\mathcal{O}(d^{1/2}T^{-1/3})$ with the average smoothness assumption. Then, we extend our analysis to distributed settings. We demonstrate that the distributed Lion optimizer and its variance reduction counterpart achieve linear speedup with respect to the number of nodes $n$, yielding convergence rates of $\mathcal{O}(d^{1/2}(nT)^{-1/4})$ and $\mathcal{O}(d^{1/2}(nT)^{-1/3})$, respectively. Additionally, we investigate a communication-efficient distributed Lion variant that utilizes sign compression for bidirectional communication. By employing unbiased sign operations, this variant achieves a convergence rate of $\mathcal{O} \left( \max \{ \frac{d^{1/4}}{T^{1/4}}, \frac{d^{1/10}}{n^{1/5}T^{1/5}} \} \right)$, and its variance-reduced counterpart can further improves the rate to $\mathcal{O}\left( \frac{d^{1/4}}{T^{1/4}} \right)$. Finally, we conduct numerical experiments to validate the effectiveness of the proposed methods.

General Machine Learning · Clustering

Xuqian Xue, Jun Zhang, Qi Cai, Zhizhong Huang, Hongming Shan, Junping Zhang

Existing contrastive multi-view clustering methods rely on a pre-defined cluster number, limiting their flexibility in real-world scenarios lacking prior knowledge. To address this, we propose GROK, a novel framework driven by a cluster decision agent for unknown-$K$ multi-view clustering. It pioneers the adaptation of group relative policy optimization (GRPO) —a reinforcement learning strategy for LLM reasoning— into the unsupervised domain to autonomously determine the optimal $K$. Specifically, the agent orchestrates the clustering process through three synergistic phases. First, in the state perception phase, we employ a structure-aware adaptive backbone to aggregate multi-view data, providing the agent with consistent and discriminative consensus observations. Second, in the group decision phase, we introduce an action space divide-and-conquer strategy and an adaptive reward function. Equipped with these mechanisms, the agent performs group sampling and relative advantage estimation within the discrete action space of candidate $K$ values, autonomously searching for the optimal $K$ via reward maximization. Finally, via geometric feedback, geometric clustering guidance mechanism transforms the agent's structural hypotheses into explicit differentiable constraints to reshape feature manifolds, thereby closing the perception-decision-feedback loop. Experimental results demonstrate that GROK achieves superior clustering performance in unknown-$K$ scenarios by autonomously exploring the underlying cluster structure.

Reinforcement Learning · Batch/Offline

Xing Lei, Jincheng Wang, Xuetao Zhang, Donglin Wang

Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world datasets are often partially observable and history-dependent, exhibiting a mix of Markovian and non-Markovian that violate standard RL assumptions. History-aware sequence models such as Decision Transformer (DT) are a natural fit for long-term dependency modeling, yet pure attention is inefficient and brittle when handling local Markovian structure and long-range context simultaneously. Although recent hybrid architectures (e.g., LSDT) introduce local extractors to improve local dependencies modeling, the fixed-window extraction cannot adapt its effective memory to varying dependency lengths in temporally heterogeneous settings, often truncating long-range context rather than compressing its content adaptively. Moreover, sequential offline GCRL faces a key bottleneck: under sparse rewards, return-to-go (RTG) becomes non-discriminative across sub-trajectories, providing little guidance signal for stitching goal-reaching behaviors from diverse demonstrations. To address these, we propose QHyer, which replaces RTG with a flow-parameterized, state-conditioned goal-reaching Q-estimator to support stitching across demonstrations, and introduces a gated Hybrid Attention-Mamba backbone that performs content-adaptive history compression while preserving local dynamics. Extensive experiments demonstrate that QHyer achieves state-of-the-art performance on both non-Markovian and Markovian datasets, validating its effectiveness for diverse scenarios.

Optimization · Non-Convex

Siqiao Mu, Diego Klabjan

The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low computational requirements. LoRA trains two "adapter" matrices that form a low-rank representation of the model parameters, thereby massively reducing the number of parameters that need to be updated at every step. Although LoRA is simple, its convergence is poorly understood due to the lack of Lipschitz smoothness, a key condition for classic convergence analyses. As a result, current theoretical results only consider asymptotic behavior or assume strong boundedness conditions which artificially enforce Lipschitz smoothness. In this work, we provide for the first time a non-asymptotic convergence analysis of the *original LoRA gradient descent* algorithm, which reflects widespread practice, without such assumptions. Our work relies on three key steps: i) reformulating the problem in terms of the outer product of the stacked adapter matrices, ii) a modified descent lemma for the "Lipschitz-like" reparametrized function, and iii) controlling the step size. With this approach, we prove that LoRA gradient descent converges to a stationary point at rate $O(\frac{1}{\log T})$, where $T$ is the number of iterations. We conduct numerical experiments to validate our theoretical findings.

Deep Learning · Large Language Models

Tao Jiang, Xinmeng Yu, Chenhao Yi, Yiling Wu, Yan Li, Ran Cheng, Dongmei Jiang, Jianguo Zhang

Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space. We propose Evolutionary Generative Merging (EvoGM), a framework that transcends manual heuristics by employing learnable generative modeling to optimize merging coefficients. Specifically,, EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates. By constructing winner-loser pairs from historical search trajectories, our framework effectively captures high-performance parameter distributions and maximizes data efficiency. This generative process is seamlessly integrated into a multi-round evolutionary pipeline, where elite merged models iteratively serve as new expert foundations. Extensive experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines, exhibiting robust performance on both seen and unseen tasks.

Deep Learning · Large Language Models

Qizheng Li, Yifei Zhang, Xiao Yang, Xu Yang, Zhuo Wang, Bowen Xian, Weiqing Liu, Jiang Bian

Fine-tuning large language models for vertical domains remains a labor-intensive and expensive process, requiring domain experts to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning, no prior work has tackled end-to-end LLM fine-tuning with agents. Can LLM-based agents automate this complete process? We frame this as a substantially open problem: agents must navigate an open-ended search space spanning data curation from diverse data sources, processing with complex tools, building a training pipeline, and iteratively refining their approach based on evaluation outcomes in rapidly growing logs—an overall scenario far more intricate than existing benchmarks. To study this question, we introduce FT-Dojo, an interactive environment comprising 13 tasks across 5 domains. We further develop FT-Agent, an autonomous system that mirrors human experts by leveraging evaluation-driven feedback to iteratively diagnose failures and refine fine-tuning strategies. Experiments on FT-Dojo demonstrate that purpose-built fine-tuning agents significantly outperform general-purpose alternatives, with FT-Agent achieving the best performance on 10 out of 13 tasks across all five domains. Ablations show that the approach generalizes effectively to 3B models, with additional insights on data scaling trade-offs and backbone sensitivity. Case analyses reveal that agents can recover from failures through cumulative learning from historical experience, while also exposing fundamental limitations in causal reasoning—highlighting both the promise and current boundaries of autonomous fine-tuning.