AI 速览：PhysCount 是一个新基准，用来检验多模态大模型能否区分图像中“可见的表象”与场景中“物理存在的实体”，并据此进行计数。
Images reveal appearances, but counting often asks about physical objects. A single entity may be visible directly, in several reflections, or through glass, so detecting every visible occurrence does not determine how many entities are present. Existing visual counting benchmarks rarely separate these two operations. We introduce PhysCount, a benchmark for evaluating whether multimodal large language models (MLLMs) can distinguish what appears in an image from what physically exists in the scene. PhysCount contains 546 real-world images and 4,595 human-written questions organized into 651 target-specific groups. For each group, annotators locate the relevant appearances, label how each is observed, and identify appearances of the same entity. Four complementary question families test the enumeration of appearances, the enumeration of physical entities, image-formation-specific counting, and appearance--entity correspondence. We measure both accuracy on each family and the proportion of groups answered entirely correctly. Across 40 MLLMs, counting visible appearances is substantially easier than recovering the identities that connect them. Even the strongest model answers every question correctly in only 13.36\% of groups. Performance declines when one entity produces many appearances or when its appearances cross observation modes. Higher image resolution improves access to visual evidence but brings limited gains in complete-group accuracy, whereas answering related questions jointly produces a marked improvement. These results expose a gap between recognizing what is visible and correctly recovering the physical entities behind those observations.
Agentic artificial intelligence built on large language models shows promise for automating Open Radio Access Network supervisory control. However, action-level safeguards alone may be insufficient: evidence acquisition consumes time and shared resources, and network changes can invalidate approvals before release. We propose Progressive Risk-Gated Actuation (PRGA), an executor-side model and contract governing intents from assessment to release or termination. PRGA combines local checks with selective retrieval of coordination evidence to reduce acquisition costs while preserving mandatory evidence requirements. Version and lease rechecks prevent release under invalidated approvals, while reevaluation requires recorded progress within each transaction's retry budget. Building on this contract, we formulate evidence allocation to maximize the expected whole-period rate of timely valid releases under risk, quality-of-service, deadline, and shared byte-budget constraints. For energy-saving and slice-protection workloads with stable daily load cycles, thresholds are selected offline and interpolated using an online load-phase estimate. On average over modeled start phases and quota levels, the allocation policy improves timely valid release rates over arrival-order fetching and an offline-selected global threshold under identical quotas and release checks. In OpenAirInterface radio emulation, an immediate scripted resend after a version-mismatch refusal raises on-time receiver delivery from 77.3% to 89.9% at modest additional command cost.
Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and producing evidence that can be independently verified. Existing research-reproduction benchmarks largely focus on AI and machine learning, where experiments share relatively homogeneous software stacks. Extending this capability across scientific disciplines introduces a different challenge: agents must operate domain-specific scientific software, make physical and numerical choices, diagnose long-running computations, and distinguish valid evidence from merely plausible outputs. We introduce PAPERBENCHX, a benchmark of 93 expert-constructed paper-reproduction tasks spanning 12 research areas across electromagnetics, photonics, chemistry, materials science, biology, and robotics. Each task provides the source paper, a public task specification, and a domain-native scientific environment involving specialized scientific software. Agents must reconstruct a key experiment, execute and diagnose it, and deliver a runnable workflow that supports the target scientific claim. To evaluate scientific validity rather than surface-level agreement, we replay every submission from scratch and score only regenerated evidence against expert-validated criteria. Across 10 frontier agent configurations, the best configuration fully reproduces only 14% tasks under the 90% threshold. Meanwhile, mean rubric scores range from 27.53% to 59.08%, indicating that substantial partial progress rarely translates into complete scientific reproduction. These results reveal a large gap between paper understanding and reliably producing reproducible scientific evidence.
When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed at many scales, while no single framework that formally describes these emerging instances exists. Its counterpart in the classical realm, iterative policy improvement, is characterized by generalized policy iteration (GPI), a framework of broad applicability with well-understood theoretical properties, but only where the update principle and the evaluation base lie outside the agent. In this paper, we propose Generalized Agent Iteration (GAI), a formal framework that describes iterative policy improvement and RSI as two cases of a single learning paradigm. GAI defines the agent as a configuration of modifiable components within a system and models the learning process as a cycle of agent evaluation and agent improvement. Two pivotal dials then distinguish the instances, in particular the systems that self-identify as RSI in recent work: whether the improving mechanism is part of the agent and whether the standard it is measured against is grounded outside it. The former dial delineates the boundary between GPI and RSI, and the latter determines a system's polarity as anchored, goal drift, or fully self-referential. Moreover, we use these coordinates to place existing systems on the same two axes and make the defects of recursive self-improvement statable one condition at a time. We see this paper as a first step toward exploring a formal characterization of RSI that rests on the classical account, makes existing systems comparable, and provides a principled basis for analyzing and designing new ones.
Multimodal videos contain rich temporal cues that can facilitate faithful fusion. However, existing video fusion methods mainly rely on short-range temporal interactions, leaving valuable long-term information underexplored. Moreover, inconsistent fusion representations can cause flickering artifacts, undermining temporal coherence. To address these coupled challenges, we propose MemoryFusion, a two-stage framework integrating cross-temporal memory learning with progressive temporal refinement. Considering the complementary roles of adjacent and distant frames, the first stage combines a Short-Term Memory Bank for local temporal guidance with a Long-Term Memory Bank that preserves reliable historical information through a fusion-oriented update strategy. To mitigate temporal fluctuations, a Temporal Smoothing Module leverages soft motion cues for coarse background stabilization. Building upon the resulting fusion prior, The second stage further employs a lightweight 3D residual Temporal Refinement Module to correct remaining temporal inconsistencies while enhancing structural details. Extensive experiments demonstrate that MemoryFusion achieves superior fusion quality and temporal consistency over existing frame-based and video-based fusion methods. The source code is publicly available at https://github.com/Meiqi-Gong/MemoryFusion.
We study satisficing regret minimization in bandits with knapsacks (BwK), where a learner sequentially selects randomized policies, i.e., distributions over arms, to obtain mean rewards above a satisficing threshold as frequently as possible while respecting finite resource budgets. The performance is measured by satisficing regret, the cumulative deficits of the selected policies' mean rewards below this threshold. Resource constraints introduce two difficulties: an algorithm can incur linear satisficing regret even with small standard regret as deficits to the threshold cannot be compensated, and random consumption can cause early resource depletion even when policies are feasible in expectation. To address these challenges, we propose SELECTwK, a general algorithmic template that uses a BwK learning oracle algorithm with sub-linear expected (standard) regret upper bound to search for and test candidate satisficing policies (i.e., policies whose mean rewards exceed satisficing threshold and whose expected resource consumption is feasible over the time horizon). Our regret analysis, supported by an LP-duality argument, establishes that SELECTwK attains constant expected satisficing regret when a satisficing policy exists. We further introduce a stronger regret condition that bounds the expected sum of positive reward deficits to the optimal one at each time step, under which SELECTwK achieves a sharper constant bound together with a sub-linear bound in the time horizon. As a complement, SELECTwK still preserves the oracle's sub-linear expected standard regret bound if the satisficing threshold is unattainable. Finally, we establish the oracle conditions and corresponding satisficing regret bound for existing finite-armed BwK and dynamic pricing algorithms, and conduct numerical experiments on dynamic pricing with limited inventory to demonstrate the empirical performance of SELECTwK.
We study in-context learning problems where a Transformer is pretrained on tasks drawn from a mixture distribution $π=\sum_{α\in\mathcal{A}} λ_α π_α$, called the pretraining prior, in which each mixture component $π_α$ is a distribution on tasks of a specific difficulty level indexed by $α$. Our goal is to understand the performance of the pretrained Transformer when evaluated on a different test distribution $μ$, consisting of tasks of fixed difficulty $β\in\mathcal{A}$, and with potential distribution shift relative to $π_β$, subject to the chi-squared divergence $χ^2(μ,π_β)$ being at most $κ$. In particular, we consider nonparametric regression problems with random smoothness, and multi-index models with both random smoothness and random effective dimension. We prove that a large Transformer pretrained on sufficient data achieves the optimal rate of convergence corresponding to the difficulty level $β$, uniformly over test distributions $μ$ in the chi-squared divergence ball. Thus, the pretrained Transformer is able to achieve faster rates of convergence on easier tasks and is robust to distribution shift at test time. Finally, we prove that even if an estimator had access to the test distribution $μ$, the convergence rate of its expected risk over $μ$ could not be faster than that of our pretrained Transformers, thereby providing a more appropriate optimality guarantee than minimax lower bounds.
Scaling model capacity has emerged as an effective approach to overcoming performance bottlenecks in industrial recommender systems. However, repeatedly training new models from scratch requires large amounts of data and substantial training resources. Parameter inheritance provides a promising route for both dense model growth and sparse conversion, yet existing methods for LLMs are primarily designed for static corpora and can suffer sharp performance drops under dynamically evolving recommendation data. To address these challenges, we propose Inherit4Rec, a parameter-inheritance framework that supports both Dense-to-Dense (D2D) growth and Dense-to-Sparse (D2S) conversion. Inherit4Rec-D2D combines hybrid growth with asymmetric training to preserve the forward function at expansion and maintain update continuity. Inherit4Rec-D2S constructs SMoE networks through co-activation-aware partitioning with a load-balancing loss, preserving dense-model capabilities while promoting balanced expert activation. Experiments on KuaiRand-1K and an industrial short-video recommendation dataset show that both transformations consistently outperform the SOTA inheritance baselines across all prediction objectives. These results demonstrate the effectiveness of Inherit4Rec for continual capacity expansion and computation-efficient sparse conversion in industrial recommender systems.
Xunpeng Yi, Yibing Zhang, Qinglong Yan, Yifan Lu, Han Xu, Jiayi Ma
Due to the inherent discrepancies in imaging viewpoints and field-of-view mismatches among multi-modal sensors, existing fusion methods have long struggled to achieve complete scene-level information integration beyond the limitation in sensor fields of view. Consequently, the generated fusion results often contain modality-specific regions and fusion artifacts, limiting the comprehensive representation of scene structures and semantic information. To address this challenge, we propose a generative registration-fusion framework, termed SeeRF. Specifically, it first introduces a deformation generation strategy based on the diffeomorphic stationary velocity field, combined with visual foundation model-guided feature extraction and a coarse-to-fine progressive multi-modal image registration module, to achieve accurate cross-modal flow estimation and generate valid field-of-view masks. Subsequently, the registration module is tightly coupled with the generative diffusion module for multi-modal completion and fusion, where the cross-modal control encoding module and the control residual feature encoder-decoder mechanism provide effective guidance. By leveraging the powerful prior modeling capability of generative diffusion models, the proposed framework overcomes the limitations imposed by shared fields of view and enables effective completion and natural fusion of non-overlapping field-of-view regions. Extensive experiments on multiple public datasets and real-world scenarios demonstrate that the proposed method achieves superior performance, validating its effectiveness, superiority, and robustness. The code will be available at https://github.com/XunpengYi/SeeRF.
Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods recover 3D geometry consistent with the input images but cannot recover unseen regions; native generation methods produce plausible 3D objects which are related but not necessarily faithful to the input images. Methods simply concatenating reconstruction and generation allow error to cascade across the two stages, instead of producing a 3D object consistent with both the distribution and the input. We propose GenSfM, which integrates image-based 3D reconstruction with a native 3D diffusion model. In particular, we use a multi-modal diffusion transformer to jointly denoise the shape latent and per-view pose latents under shared self-attention, grounding generated geometry in the observed views while using object-level priors to infer unobserved regions. A compact 3D-native UV-volume tokenization keeps the joint sequence small as views are added, and a pose-aware stage refines geometry and texture by sampling per-voxel image features at the recovered camera poses. On Toys4k and GSO, for $4$ uncalibrated views, GenSfM improves novel-view PSNR by $3.2$-$4.5$ dB and reduces median Chamfer distance by $2.8$-$3.8\times$ over a strong native-3D generation baseline, while recovering input-view poses over $96\%$ Acc@$5^\circ$ without any external pose-estimation backbone, post-hoc optimization, or known intrinsics. Project page: https://dotb1ue.github.io/GenSfm/.
Zihan Gu, Lulu Zhao, Tianyi Ma, Hua Zhang, Wenbo Su, Yanan Cao, Yue Hu
Grokking is a delayed transition from memorisation to generalisation. A network first fits observed examples while remaining near chance on held-out inputs, then generalises abruptly. Prior work has focused mainly on this delay, finding that the network's main loss becomes weight decay after the fitting phase. We name the solution to this optimization problem as the minimum-norm endpoint, and study which tasks make all minimum-norm endpoints generalise from partial observations. Specifically, we model pairwise input tasks as edge colourings of $K_{q,q}$, with Latin colourings as our structured family, and classify each observed instance as all-good, mixed, or no-good by its endpoint set. Furthermore, we prove two contrasting results: (1) Finite-abelian-group families are asymptotically all-good from partial observations; (2) Under a uniform random Latin square, all-good tasks become asymptotically rare for observation-based learners, leaving mixed or no-good behaviour. Moreover, experiments show that relabellings of addition generalise despite their dense polynomial representations. Finally, on tasks of composite order, finite-training results suggest that predictors learn a coarse part of the output before the full label.
We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.
Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou, Wenjun Huang, Tianyi Ma, Yicheng Qiao, Zheda Mai 等 18 位作者
Visual large language models (VLLMs) are increasingly used as embodied agents, yet industrial warehouses demand more than reaching a goal: agents must navigate safely around moving workers and vehicles. To evaluate embodied agents' goal reaching and safety, we introduce IndustryNav, a simulation environment with 24 warehouse scenes for closed-loop navigation to specified destinations. Alongside task success and efficiency, we introduce safety-aware metrics that capture collisions and near-collision warnings along each trajectory. Experiments with eleven leading open- and closed-source VLLMs and three navigation baselines show that agents can reach their goals yet collide with moving obstacles, exposing a gap between success and safe navigation. This gap matters in safety-critical settings, where a single collision can end the task. IndustryNav also supports policy learning through automated oracle trajectories and simulator interaction, with held-out scenes for generalization tests. These experiments show that policies can succeed on new routes in familiar warehouses yet fail to transfer to held-out layouts, making cross-scene generalization an open challenge.
Han Zhang, Zihan Gu Institute of Information Engineering, Chinese Academy of Sciences, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu Shanghai Jiao Tong University, Xinyan Zhang independent, Yuhao Wei, Cheng Hua Shanghai Jiaotong University
While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. To address this issue, we introduce Neo-Classic, an evaluation benchmark that combines a constructionist Out-of-Sample (OOS) dataset with a suite of reverse understanding probes. Unlike traditional benchmarks that rely on verification or generation over historical corpora, Neo-Classic comprises strictly metrical poetry authored by contemporary experts, reducing the possibility of direct retrieval. We evaluate state-of-the-art models, including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2, across five behavioral probes designed to test hierarchical constraint satisfaction. Our results reveal two primary limitations. First, a performance gap of 20%–50% emerges when models transition from historical to contemporary texts. Second, models exhibit substantial difficulties in discourse-level ordering tasks, with standard accuracy remaining low (0–13%). Although expert-level guidance improves the performance of reasoning-enhanced models to 36%, a notable gap with human experts persists. These findings suggest that while current LLMs capture local formal patterns, they struggle with global hierarchical planning required for robust Linguistic-Aesthetic Reasoning.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zihan Gu Institute of Information Engineering, Chinese Academy of Sciences, TianYi Zhang University of the Chinese Academy of Sciences, Xinyan Zhang independent, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu Shanghai Jiao Tong University, Tianyi Ma 等 11 位作者
Model editing provides a promising mechanism for updating large language models (LLMs) without expensive retraining. Existing approaches, particularly locate-and-edit methods based on least-squares optimization, aim to introduce targeted knowledge changes while preserving pre-trained behavior. In this work, we show that this objective is fundamentally fragile under standard single-edit evaluation protocols. We first develop a unified theoretical framework that characterizes activation-based editing as a constrained intervention on intermediate representations. Within this framework, we demonstrate that least-squares edits cannot, in general, isolate target updates from unrelated activations, giving rise to unavoidable interference that accumulates with successive edits. Crucially, this degradation can remain undetected in single-edit settings when assessed using conventional success and locality metrics. To expose such hidden instabilities, we introduce an uncertainty-based evaluation protocol that combines structured semantic perturbations with uncertainty quantification based on Sampling with Perturbation for UQ. By measuring edit-induced growth in aleatoric and epistemic uncertainty, our method reveals local knowledge conflicts that are invisible to existing benchmarks. Extensive experiments across multiple models, datasets, and editing algorithms show that both least-squares and other parameter-update-based methods consistently increase post-edit uncertainty. Together, our results suggest that current evaluation practices substantially overestimate the reliability of single-edit model editing, and that uncertainty-based diagnostics are necessary for assessing edit stability.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan, Zehong Wang, Tianyi Ma University of Notre Dame, Keerthiram Murugesan International Business Machines, Vincent Galassi, Chuxu Zhang University of Connecticut 等 9 位作者
Large language models (LLMs) and agent-based frameworks have advanced rapidly, enabling diverse applications. Yet, with the proliferation of models and agentic strategies, practitioners face substantial uncertainty in selecting the best configuration for a downstream task. Prior studies show that different agents and backbones exhibit complementary strengths, and that larger models are not always superior, underscoring the need for adaptive routing mechanisms. Existing approaches to agent routing, however, often emphasize cost efficiency while overlooking the fine-grained contextual and relational structure inherent in QA tasks. In this paper, we propose AgentRouter, a framework that formulates multi-agent QA as a knowledge-graph–guided routing problem supervised by empirical performance signals. Specifically, we convert QA instance into a heterogeneous knowledge graph that jointly encodes queries, contextual entities, and agents, and then train a heterogeneous graph neural network (GNN) to propagate information across node types and produce task-aware routing distributions over agents. By leveraging soft supervision and weighted aggregation of agent outputs, AgentRouter learns principled collaboration schemes that capture the complementary strengths of diverse agents. Extensive experiments demonstrate that our framework consistently outperforms single-agent and ensemble baselines, while generalizing across benchmarks and LLM backbones. These results highlight the effectiveness and robustness of graph-supervised multi-agent routing for question answering. Our code repo is available at https://anonymous.4open.science/r/AgentRouter.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tianyi Ma Michigan State University, Yue Zhang, Zehao Wang KU Leuven, Parisa Kordjamshidi Michigan State University
Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments. While recent progress has been driven by large-scale pre-training and data augmentation, current methods still struggle to generalize to unseen scenarios, particularly when complex spatial and temporal reasoning is required. In this work, we propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. Our method decomposes navigation into a set of interpretable atomic skills (e.g., Vertical Movement, Area and Region Identification, Stop and Pause), each handled by a specialized agent. To support targeted skill training without manual data annotation, we construct a synthetic dataset pipeline that generates diverse, linguistically natural, skill-specific instruction-trajectory pairs. We then introduce a novel training-free Vision-Language Model (VLM)-based router, which dynamically selects the most suitable agent at each time step by aligning sub-goals with visual observations and previous actions. SkillNav obtains competitive results on commonly used benchmarks and establishes state-of-the-art generalization to the GSA-R2R, a benchmark with novel instruction styles and unseen environments.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表