AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ICML 2026

Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment

Zhuo Zuo, Li Yue, Wenhao Zheng, Chenpeng Wang, Xianggen Liu

Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason is the training objective: standard cross-entropy treats numeric tokens as unstructured categories and ignores the metric structure of their values. We address this mismatch by proposing **S**mooth **M**aximum **M**ean **D**iscrepancy (**SMMD**), which builds on the classic MMD by incorporating value-distance kernels over numeric tokens and graph-based smoothness. With this kernel defined over a numeric sub-vocabulary, SMMD aligns the predicted numeric distribution to the target via kernel matching and smooths the prediction--target residual over the induced kernel graph to encourage local consistency. We evaluate SMMD on four numeric-target tasks---mathematical reasoning, arithmetic calculation, clock-time recognition, and chart question answering---across multiple open-weight LLM and VLM backbones. SMMD consistently improves accuracy over both cross-entropy and recent numeric-target losses; analyses show complementary effects between MMD and smoothness and underscore the importance of distance-based kernel design.

ICML 2026

Do-Prompt: Causal Interventions Meet Variational Prompt Bottlenecks

Xueting Chen, Jun-Jie Huang, Yan Yan, Long Lan, Yuhua Tang, Wenjing Yang

Multi-modal prompt learning is a parameter-efficient approach to adapting large vision-language models to downstream classification tasks. However, prompts can inadvertently evolve into a high-capacity pathway that encodes environment-dependent spurious correlations, which are predictive only in the source domain and thereby undermine transferability. To address this issue, this paper introduces **Do-Prompt**, a *compress-and-intervene* framework that brings together variational bottlenecks and causal interventions for robust prompt tuning. We model prompts as stochastic latent variables and impose a *variational prompt bottleneck* to explicitly regulate the information transmitted through prompts, effectively mitigating their tendency to memorize spurious nuisance cues. Building on this capacity constraint, we propose lightweight *prompt-level interventions* by perturbing the environment-related prompt components and enforcing prediction consistency under these *do*-style perturbations. This synergistic integration encourages reliance on task-stable, invariant semantics rather than spurious prompt content. Notably, Do-Prompt is plug-and-play compatible with existing multi-modal prompt tuning pipelines and introduces negligible computational overhead. Extensive experiments on base-to-novel generalization, cross-dataset transfer, and ImageNet distribution shifts demonstrate consistent performance gains, with particularly notable improvements on datasets exhibiting pronounced domain or texture biases.

ICML 2026

Two-Stage Unit Tying for Simplifying Differentiable Logic Gate Networks

Seungheon Lee, Jeongmin Sun, Jaeyong Chung

Differentiable logic gate networks map directly to gate-level circuits, enabling ultra-low-latency inference, yet their logic footprint often exceeds FPGA capacity budgets. Tightly fitting a trained model to a target FPGA requires a post-training mechanism to trade off network complexity and accuracy—analogous to pruning in standard neural networks. To this end, we introduce *unit tying*: a simplification that forces selected gates to constants (0 or 1), enabling constant propagation and downstream logic elimination. However, we observe that naively extending pruning criteria to logic networks is unreliable under such near-discrete modifications. We therefore propose a two-stage algorithm for unit tying: (i) a fast Gauss–Newton screening step under a teacher-referenced logit-distortion objective that constructs a high-recall overshoot set and (ii) a refinement step that corrects approximation and interaction-driven errors using a small number of finite-difference evaluations. On CIFAR-10 and MNIST, our method consistently improves the accuracy–area trade-off over common saliency baselines, yielding substantial post-synthesis LUT reductions of up to 48% on CIFAR-10 and 43% on MNIST, with modest accuracy degradation.

ICML 2026

ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling

Yuchen Yang, Yaru Zhao, Pu Yang, Shaowei Wang, Zhi-Hua Zhou

While Mixture-of-Experts (MoE) architectures substantially bolster the expressive power of large-language models, their prohibitive memory footprint severely impedes the practical deployment on resource-constrained edge devices, especially when model behavior must be preserved without relying on lossy quantization. In this paper, we present ZipMoE, an efficient and semantically lossless on-device MoE serving system. ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters via a caching-scheduling co-design with provable performance guarantee. Fundamentally, our design shifts the paradigm of on-device MoE inference from an I/O-bound bottleneck to a compute-centric workflow that enables efficient parallelization. We implement a prototype of ZipMoE and conduct extensive experiments on representative edge computing platforms using popular open-source MoE models and real-world workloads. Our evaluation reveals that ZipMoE achieves up to 72.77% inference latency reduction and up to $6.76\times$ higher throughput than the state-of-the-art systems. Our code is available at: https://github.com/npnothard/ZipMoE-ICML26.

ICML 2026

WhisperSplat: Lossless Steganography in 3D Gaussian Splatting

Nicole Meng, Ronak Sahu, Miao Yin, Faysal Hossain Shezan, Yingjie Lao

We present WhisperSplat, the first lossless steganography method for 3D Gaussian Splatting (3DGS) models that hides a full‐resolution 2D image in a single view without any degradation of the model's rendering quality elsewhere. Prior work embeds data by retraining or modifying model weights, altering novel‐view synthesis fidelity and limiting capacity. Instead, we learn a small, view‐specific noise key applied to each Gaussian's spherical‐harmonic (SH) features while keeping all other views remain indistinguishable from the original renders. We further propose a Gradual Pixel Perturbation (GPP) strategy with a cosine-decay schedule, bootstrapping fast divergence from the clean render before transitioning to a combined reconstruction and SSIM loss. Unlike prior works that are highly dependent on accurate and large pretrained decoders, our method is able to recover the hidden image through rendering with noise key, and an optional lightweight refiner to enhance recovery image quality. Across nine standard 3DGS data scenes, WhisperSplat demonstrates superior hidden image recovery quality without sacrifice in clean 3DGS model performance, when compared to prior work such as GS-Hider and KeySS.

ICML 2026

Memory Savings at What Cost? A Study of Alternatives to Backpropagation

Kunjal Panchal, Sunav Choudhary, Yuriy Brun, Hui Guan

Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language model (LLM) fine-tuning, yet their benefits are typically evaluated only against standard backpropagation (BP), omitting memory-efficient variants such as activation checkpointing. We present a unified theoretical and empirical comparison of BP, checkpointed BP, FmAD, and ZO for LLM and vision-language model training, showing that while FmAD and ZO reduce activation memory, they trade memory for higher computational cost and longer wall-clock time to convergence, resulting in lower accuracy and slower training, especially under constrained perturbation budgets. Across models, BP with checkpointing outperforms FmAD and ZO variants, including variance-reduced methods, achieving up to 31.1% higher accuracy, 34.8% faster convergence, and 3.8$\times$ fewer computations at comparable memory usage, while also revealing instability-related failure modes in FmAD and ZO. Overall, our results correct a one-sided benchmarking narrative by showing that memory-efficient methods entail fundamentally different trade-offs, and that ignoring these distinctions has led to misleading conclusions about LLM optimization in prior work.

ICML 2026

Gradient Flow Sampler-based Distributionally Robust Optimization

Zusen Xu, Jia-Jie Zhu

We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Monte Carlo sampling and statistical optimal transport, we show that our theoretical framework can be implemented as practical algorithms for sampling from worst-case distributions and, consequently, DRO. While numerous previous works have relied on dual reformulation techniques, we contribute a sound and complete gradient flow view based on SDEs or PDEs that can be used to construct new algorithms for general, potentially non-convex, losses. Without loss of generality, we solve a class of Wasserstein and entropy-regularized DRO problems using the recently-discovered Wasserstein Fisher-Rao and Stein variational gradient flows. Notably, we also show some simple reductions of our framework recover exactly previously proposed popular DRO methods, and provide new insights into their theoretical limits and optimization dynamics of DRO. Numerical studies based on stochastic gradient descent on machine learning tasks provide empirical backing for our theoretical findings.

ICML 2026

Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization

Nadhir Hassen, Johan W. Verjans

Generative Flow Networks (GFNs) offer a powerful paradigm for diverse sampling, yet they often exhibit instability and poor convergence when applied to stochastic or sparse-reward environments. To mitigate the high variance inherent in these settings, we propose a fundamental re-framing of the GFlowNet training objective within the frequency domain. We present \textbf{Spectral Time-Dependent GFlowNets (ST-GFNs)}, a framework that leverages Fourier analysis to enforce smoothness and stability in learned policies. Our theoretical analysis proves that our proposed spectral loss is mathematically equivalent to regularized value iteration, acting as a principled low-pass filter that separates signal from noise. Furthermore, we tackle the challenge of exploration in sparse landscapes by introducing a novel autocorrelated intrinsic reward derived from the Wiener-Khinchin theorem. Through extensive experiments ranging from adversarial games and noisy sequence generation to high-dimensional single-cell perturbation modelling, we demonstrate that ST-GFNs significantly outperform existing baselines in terms of robustness, sample efficiency, and mode discovery.

ICML 2026

User-Aware Active Knowledge Acquisition for Emotional Support Dialogue

Mufan Xu, Kehai Chen, Jiahao Hu, Xinchao Xu, Muyun Yang, Tiejun Zhao, Min Zhang

Emotional support plays an important role in dialogue systems, and its success depends on adapting to a user’s evolving and implicit needs across multi-turn interactions while leveraging the strong reasoning capacity of large language models. However, since signals about user needs are often weak, indirect, and can only be disambiguated through multi-turn interaction, existing emotional support methods often struggle to acquire and generalize relevant conversational knowledge efficiently. To bridge this gap, we introduce User-Aware Active Knowledge Acquisition (UKA), a gradient-free active dialogue learning framework that explicitly represents uncertainty about user needs and incorporates active learning into both knowledge acquisition and response selection. We propose a Theory-of-Mind uncertainty estimation mechanism that allows the model to prioritize responses, thereby eliciting more informative user feedback. UKA is capable of efficiently exploring user-aligned conversational knowledge during training while maintaining robustness at test time. Experiments across multiple dialogue benchmarks and model architectures demonstrate that our approach consistently outperforms strong baselines in dialogue quality and user alignment.

ICML 2026

Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference Passages

Doyoung Kim, Youngjun Lee, Joeun Kim, Jihwan Bang, Hwanjun Song, Susik Yoon, Jae-Gil Lee

Conversational query reformulation (CQR) has become indispensable for improving retrieval in dialogue-based applications. However, existing approaches typically rely on reference passages for optimization, which are **impractical** to acquire in real-world scenarios. To address this limitation, we introduce a novel **reference-free** preference optimization framework ***DualReform*** that generates **pseudo reference passages** from **commonly-encountered** conversational datasets containing only queries and responses. DualReform attains this goal through two key innovations: (1) **response-based inference**, where responses serve as proxies to infer pseudo reference passages, and (2) **response refinement via the dual-role of CQR**, where a CQR model refines responses based on the shared objectives between response refinement and CQR. Despite not relying on reference passages, ***DualReform*** achieves 96.9--99.1% of the retrieval accuracy attainable only with reference passages and surpasses the state-of-the-art method by up to 31.6%.

ICML 2026

Experience Augmented Policy Optimization for LLM Reasoning

Jinda Lu, Kexin Huang, Junkang Wu, Shuo Yang, Jinghan Li, Chiyu Ma, Shaohang Wei, Xiang Wang, Guoyin Wang, Jingren Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing RLVR methods typically rely on on-policy optimization from scratch, resulting in high sampling costs and inefficient utilization of accumulated experience. As model capabilities and policy behaviors evolve during training, recent attempts to reuse experience via fixed reasoning trajectories further suffer from policy mismatch. Motivated by these limitations, we argue that experience in RLVR should not be reused as fixed reasoning trajectories, but instead expressed in a policy-adaptive manner. In this work, we propose Experience-Augmented Policy Optimization (EAPO), which leverages a prior RL-optimized policy as an action-level experience prior and selectively injects experience at critical decision points during rollout. To ensure stable and unbiased learning from experience-augmented rollouts, EAPO further incorporates an adapted importance sampling scheme. Experiments on using Qwen-2.5-math 7b and Qwen-3-8B on five different benchmarks demonstrate that EAPO consistently improves reasoning performance over state-of-the-art RLVR methods.

ICML 2026

Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination

Mengqi Chen, Thomas Berrett, Theodoros Damoulas, Michele Caprio

Distributionally robust optimisation (DRO) minimises the worst-case expected loss over an ambiguity set that can capture distributional shifts in out-of-sample environments. While Huber (linear-vacuous) contamination is a classical minimal-assumption model for an $\varepsilon$-fraction of arbitrary perturbations, including it in an ambiguity set can make the worst-case risk infinite and the DRO objective vacuous unless one imposes strong boundedness or support assumptions. We address these challenges by introducing bulk-calibrated credal ambiguity sets: we learn a high-mass bulk set from data while considering contamination inside the bulk and bounding the remaining tail contribution separately. This leads to a closed-form, finite $\mathrm{mean}+\sup$ robust objective and tractable linear or second-order cone programs for common losses and bulk geometries. Through this framework, we highlight and exploit the equivalence between the imprecise probability (IP) notion of upper expectation and the worst-case risk, demonstrating how IP credal sets translate into DRO objectives with interpretable tolerance levels. Experiments on heavy-tailed inventory control, geographically shifted house-price regression, and demographically shifted text classification show competitive robustness-accuracy trade-offs and efficient optimisation times, using Bayesian, frequentist, or empirical reference distributions.

ICML 2026

A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization

Zhiyao Zhang, Myeung Suk Oh, Zhen Qin, Jiaxiang Li, Xin Zhang, Jia Liu

In recent years, bilevel optimization (BLO) has attracted significant attention for its broad applications in machine learning. However, most existing works on BLO remain confined to the single-task setting and rely on the lower-level strong convexity assumption, which significantly restricts their applicability to modern machine learning problems of growing complexity. In this paper, we make the first attempt to extend BLO to the multi-task setting under a relaxed lower-level general convexity (LLGC) assumption. To this end, we reformulate the multi-task bilevel learning (MTBL) problem with LLGC into an equality constrained multi-objective optimization (ECMO) problem. However, ECMO itself is a new problem that has not yet been studied in the literature. To address this gap, we first establish a new Karush–Kuhn–Tucker (KKT)-based Pareto stationarity as the convergence criterion for ECMO algorithm design. Based on this foundation, we propose a weighted Chebyshev (WC)-penalty algorithm that achieves a finite-time convergence rate of $\mathcal{O}(ST^{-\frac{1}{2}})$ to KKT-based Pareto stationarity in both deterministic and stochastic settings, where $S$ denotes the number of objectives, and $T$ is the total iterations. Moreover, by varying the preference vector over the $S$-dimensional simplex, our WC-penalty method systematically explores the Pareto front. Finally, solutions to the ECMO problem translate directly into solutions for the original MTBL problem, thereby closing the loop between these two foundational optimization frameworks.

ICML 2026

SpaEF: Spatially Resolved Transcriptomics Data Element-Wise Denoising Framework Powered by Large Models

Zekuan Shang, Xiaosong Han, Liupu Wang, Wei Du, Peng Zhao, Yuanshu Li, Yubin Xiao, Xuan Wu, You Zhou

For denoising Spatially Resolved Transcriptomics (SRT) data, existing methods often construct spot and gene graphs to model inter-spot and inter-gene relationships, respectively. However, these methods often introduce spurious similarity biases among spots when constructing the spot graph and fail to capture nonlinear relationships among genes when constructing the gene graph. Moreover, ineffective graph fusion strategies further bottleneck denoising performance. To address these challenges, we propose SpaEF, which innovatively constructs spot and gene graphs with two Large Models (LMs) to inject prior knowledge for mitigating biases and capture nonlinear relationships, and then fuses them with the proposed element-wise graph autoencoder. As far as we know, SpaEF is the first SRT denoising method that utilizes pre-trained LMs to construct spot and gene graphs. Experiments on four real-world datasets with corresponding downstream tasks demonstrate that SpaEF not only outperforms SOTA denoising methods in accuracy but also exhibits strong robustness across tasks.

ICML 2026

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models

Zhaoyang Li, Yanjun Li, Wangkai Li, Yujia Chen, Tianzhu Zhang

Vision-Language Models (VLMs) are costly at inference time because they must process long sequences of visual tokens. Existing token pruning methods often degrade under high compression by blindly discarding information, breaking spatial structure or collapsing diversity. We propose SpecFlow, a training-free framework that shifts the paradigm from destructive pruning to conservative condensation, strictly enforcing spatial coverage and statistical conservation to ensure stability. Treating visual tokens as nodes in a $k$NN graph, SpecFlow (i) computes a stable importance field via spectral heat flow to preserve structural coherence, (ii) allocates budgets via adaptive spatial partitioning to guarantee coverage, and (iii) aggregates discarded information into coreset sinks to maintain statistical conservation. The method is plug-and-play, requires no fine-tuning, and is compatible with FlashAttention. Experiments confirm that our SpecFlow outperforms SOTA methods across tasks, VLM architectures, and pruning ratios. Notably, LLaVA-1.5 with SpecFlow retains 95.6\% of original performance despite pruning 88.9\% of visual tokens, offering an exceptional efficiency-accuracy balance.

ICML 2026

DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and Exploitation

Li Yang, Jialong Sun, Chuhai Cai, Xinyang Liu, Yichen Li, Bowen Peng, Jialong Li, Bo Liu

Decentralized Federated Learning (DFL) enables collaborative model training across connected clients without a central server, effectively mitigating communication bottlenecks and avoiding the single point of failure in Centralized Federated Learning (CFL). However, existing DFL methods mostly focus on parameter averaging with compromised update directions, which limits their performance potential due to insufficient exploration of the loss landscape, especially for complex models. We observe that layer exchanges among clients enhance exploration while introducing instability due to highly diverse update directions. To address these limitations, we propose Decentralized Layer-wise Fusion (DecFus), the first DFL framework that unifies layer-level exchange and averaging to balance exploration and exploitation. DecFus dynamically transitions the decentralized training process from exploration-dominant to exploitation-dominant phases, guided by the loss variance among connected neighbors. Furthermore, a layer-wise fusion strategy, informed by pairwise cosine similarity, categorizes all layers into two groups: an exchange group for exploration and an averaging group for exploitation. Specifically, we theoretically establish the convergence of DecFus without relying on the common assumption in existing literature that the aggregation matrix must be doubly stochastic. Extensive experiments demonstrate that DecFus achieves superior performance in both IID and non-IID scenarios, substantially outperforming existing CFL and DFL methods.

ICML 2026

LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection

Jinjie Fang, Chengxun Jin, Tianxing Man, Yi Chang, Bin Gu

Zeroth-order (ZO) optimization offers a more memory-efficient alternative to first-order methods for fine-tuning large language models (LLMs). Recent ZO methods, exemplified by LOZO, estimate gradients within low-rank subspaces to align with the low-rank structure of LLM gradients. However, these methods rely on randomly generated subspaces of a fixed rank, which provides no guarantee of alignment with the actual dominant subspaces of the gradients; essentially, they remain ZO gradient descent with stochastic subspace sampling. To more effectively exploit the low-rank nature of LLM gradients, we propose \textbf{LOZO+}, an efficient \textbf{ZO} fine-tuning algorithm for LLMs that incorporates greedy \textbf{Lo}w-Rank subspace selection. Specifically, LOZO+ leverages loss-based feedback to assess alignment between candidate directions and the dominant low-rank gradient subspaces, and employs an adaptive thresholding criterion to retain only directions yielding substantial gradient descent, thereby steering ZO optimization toward more effective convergence. Importantly, we establish a theoretical framework that characterizes the convergence behavior of LOZO+, formally prove its superiority over existing methods. Extensive experiments demonstrate that LOZO+ consistently outperforms existing ZO methods and achieves performance competitive with FO algorithm, while retaining the memory efficiency inherent to ZO optimization.

ICML 2026

Phase-Type Variational Autoencoders for Heavy-Tailed Data

Abdelhakim Ziani, Andras Horvath, Paolo Ballarini

Heavy-tailed distributions are ubiquitous in real-world data, where rare but extreme events dominate risk and variability. However, standard Variational Autoencoders (VAEs) employ simple decoder distributions (e.g., Gaussian) that fail to capture heavy-tailed behavior, while existing heavy-tail-aware extensions remain restricted to predefined parametric families whose tail behavior is fixed a priori. We propose the Phase-Type Variational Autoencoder (PH-VAE), whose decoder distribution is a latent-conditioned Phase-Type (PH) distribution—defined as the absorption time of a continuous-time Markov chain (CTMC). This formulation composes multiple exponential time scales, yielding a flexible, analytically tractable decoder that adapts its finite-range tail behavior directly from the observed data. Experiments on synthetic and real-world benchmarks demonstrate that PH-VAE accurately approximates diverse heavy-tailed distributions, significantly outperforming Gaussian, Student-t, and extreme-value-based VAE decoders in modeling observed tail behavior and extreme quantiles. In multivariate settings, PH-VAE captures realistic cross-dimensional tail dependence through its shared latent representation. To our knowledge, this is the first work to integrate Phase-Type distributions into deep generative modeling, bridging applied probability and representation learning.

ICML 2026

DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs

Kaiqi Chen, Yang Qin, Changhao He, Xi Peng, Peng Hu

Multimodal Large Language Models (MLLMs) frequently produce hallucinations (i.e., assertions that contradict the image or facts), undermining reliability in high-risk applications. Existing detection approaches typically feed images and texts jointly and estimate hallucination scores by measuring the consistency of model outputs. However, because the visual module often lags behind the language module in understanding and reasoning, MLLMs can repeatedly produce similar yet incorrect answers, yielding overestimated trustworthiness and missed detections. To address this, we propose a simple yet effective model-agnostic method, dubbed Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness (DOUBT). DOUBT first employs Object-level Understanding and Bridging (OUB), a two-step prompting scheme that decouples object recognition from relational reasoning by prompting the model to identify objects and then reason based on them. It further introduces a von Mises-Fisher (vMF)-based trustworthiness metric, which is more stable than semantic entropy metrics in small-sample settings. Extensive experiments and ablation studies on multiple benchmarks show that DOUBT consistently outperforms state-of-the-art baselines, demonstrating its robustness and generalizability for hallucination detection in MLLMs. The code is available at https://github.com/XLearning-SCU/2026-ICML-DOUBT.

ICML 2026

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

Shiva Krishna Reddy Malay, Shravan Nayak, Sagar Davasam, Srinivas Sunkara, Sai Rajeswar

The rapid evolution of Large Language Models (LLMs) has shifted their role from passive information providers to active agents capable of executing complex workflows. However, the realization of a true "AI worker" is currently hindered by benchmarks that fail to capture the intricacy of professional environments, which demand long-horizon planning, complex tool usage, and adherence to strict access protocols. To bridge this gap, we introduce EnterpriseOps-Gym, a benchmark environment designed to evaluate agentic planning in realistic enterprise settings. EnterpriseOps-Gym provides: (i) 1,150 expert-curated tasks across eight interconnected domains (including HR, IT, Customer Service and productivity tools) that require managing persistent state and adhering to strict outcome-based verification logic; and (ii) a high-fidelity, containerized sandbox environment hosting 164 database tables and 512 functional tools. Our evaluation reveals critical limitations in state-of-the-art models: even the top-performing Claude Sonnet~4.5 achieves only 34.1\% success, struggling significantly with planning consistency, error recovery, and policy constraints. Furthermore, we observe that agents frequently fail to refuse infeasible tasks, leading to unintended and potentially harmful side effects on the system. These findings indicate that current agents are not yet ready for enterprise deployment. By releasing EnterpriseOps-Gym, we provide a concrete testbed to advance the reliability of autonomous agents in professional workflows.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.