Bingran You, Wenjun Ke, Ria Rosenauer, Bo Liu, Wenbo Chen, Min Chen, Shuqi Xu, Yue Ma 等 72 位作者
AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics. Each task requires agents to review the literature, develop a research plan, conduct research and experiments, and produce structured outputs and scientific manuscripts. Combining deterministic verifiers with expert-authored rubrics, FrontierPhysics evaluates whether agents' research is correct and publishable. Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts. Manual review of agent trajectories shows that frontier agents' main weaknesses are insufficiently rigorous reasoning and limited expert intuition, rather than gaps in physics knowledge or execution errors.
EEG-based brain-computer interfaces support a broad range of applications, yet designing decoding architectures that perform well across diverse tasks remains challenging. We introduce AutoBCI, an agentic framework in which a Designer Agent and a Forecaster Agent support the discovery and selection of EEG decoding architectures across tasks. The Designer Agent performs Pool-Guided Architecture Discovery (PGAD), generating and refining architectures through training and validation across multiple EEG tasks, such as emotion recognition, motor imagery, and sleep staging. The Forecaster Agent performs Performance Estimation from Early Knowledge (PEEK), using architecture code, the training protocol, and early learning curves to predict full-budget validation performance and select promising candidates for continued training. Across 14 EEG datasets spanning motor imagery, emotion recognition, and sleep staging, we evaluate AutoBCI with six LLMs, including Opus 5.5 and GPT 5.6 Sol, and compare the architectures selected by the search procedure against ten baselines: six conventional EEG models and four foundation models. The architecture discovered by AutoBCI with Claude Opus 5.5 achieves 64.16% average test balanced accuracy (bAcc), compared with 63.87% for REVE, the strongest baseline on this metric. Using ten observed epochs, PEEK reduces mean absolute error in predicting average validation bAcc from 2.20 to 1.36 percentage points, a 38.1% reduction relative to the best-observed-score baseline. Code is available at https://github.com/Jiang-Muyun/AutoBCI
Gengyu Rao, Ghadeer Ahmed H Alabandi, Su Ann Chong, Thomas Huber, Kailash Gogineni, Subhajit Dutta Chowdhury, Saleel Kudchadker, Suchita Pati 等 31 位作者
Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus
Rong Shan, Aofan Yu, Bo Chen, Kuo Cai, Qiang Luo, Ruiming Tang, Han Li, Weiwen Liu 等 10 位作者
Recommender systems (RecSys) are increasingly emphasizing scaling, leveraging larger architectures and more interaction data to improve personalization. Yet, despite the optimizer's pivotal role in training, modern RecSys pipelines almost universally default to Adam/AdamW, with limited scrutiny of whether these choices are truly optimal for recommendation. In this work, we revisit optimizer design for scalable recommendation and introduce MuonRec, the first framework that brings the recently proposed Muon optimizer to RecSys training. Muon performs orthogonalized momentum updates for 2D weight matrices via Newton-Schulz iteration, promoting diverse update directions and improving optimization efficiency. We develop an open-source training recipe for recommendation models and evaluate it across both traditional sequential recommenders and modern generative recommenders. Extensive experiments demonstrate that MuonRec reduces converged training steps by an average of 32.4\% while simultaneously improving final ranking quality. Specifically, MuonRec yields consistent relative gains in NDCG@10, averaging 12.6\% across all settings, with particularly pronounced improvements in generative recommendation models. These results consistently outperform strong Adam/AdamW baselines, positioning Muon as a promising new optimizer standard for RecSys training. Our code is available.
Wenhao Li, Qinglin Jia, Chenghou Jin, Zihong Xian, Jiezhou Ji, Yanzhi Liu, Zezheng Wang, Bo Chen 等 12 位作者
Modeling lifetime user behavior sequences is essential for capturing long-range preferences in industrial recommendation, yet sequences containing up to 100K interactions make target-aware ranking prohibitively expensive. Search-based methods that retrieve from raw sequences incur candidate-dependent costs that grow with sequence length, whereas latent compression methods reduce computation at the expense of item-level addressability. We propose ECHO (Efficient Cascade with Homogeneous Operators), a framework that balances efficiency and fine-grained retrieval by retaining a subset of original event records per user through a Distilled Selector (DS) and retrieving a smaller set of target-relevant records for each candidate through a Target-aware Fine-grained Retriever (TFR). DS is supervised by a candidate-aware full-history teacher via per-target distillation, enabling target-aware user-level selection without requiring full-history computation for every candidate. The retriever and target-attention scorer share the relevance parameters learned by the teacher, ensuring consistent relevance estimation throughout the cascade. At a sequence length of 100K, ECHO reduces online sequence-branch FLOPs by approximately 160 times compared with a representative end-to-end model. Three deployment optimizations, including common user inputs, compact record encoding, and key-side projection absorption, further reduce memory, storage, and data-movement overhead. Experiments on KuaiRand-1K and an industrial-scale short-video platform demonstrate relative GAUC improvements ranging from 0.113% to 1.520% over state-of-the-art baselines across multiple tasks. Furthermore, online A/B tests in two production scenarios, Kuaishou and Kuaishou Lite, show that ECHO improves app usage time by 0.240% and 0.373%, respectively.
This paper considers online intrusion-risk assessment and graded warning for unmanned aerial vehicles under bounded measurement attacks. To address this problem, we develop a monitoring framework that combines trusted state estimation, attack-aware risk assessment, and probabilistic signal temporal logic (PrSTL). Trusted observations support recursive state estimation, while potentially attacked observations inform integrity testing and intrusion-risk assessment. The key contribution is a confidence-set construction that combines normalized innovation statistics with physical attack bounds to characterize admissible measurement biases. The resulting family of bias-corrected Gaussian posteriors yields an upper bound on the probability of occupying a no-fly zone or its surrounding safety margin. Confidence guarantees and finite-cover numerical certificates quantify the reliability of this risk envelope, which is evaluated with or without an integrity alarm. The PrSTL monitor analyzes the resulting risk sequence to distinguish ordered, persistent, and repeated risk and produces graded warnings with explicit robustness margins and supporting windows. We validate the monitor in flight experiments with a Crazyflie quadrotor tracked by a Vicon motion capture system. Controlled comparisons quantify the contributions of individual monitoring components. Prescribed risk profiles verify the temporal semantics and illustrate how distinct risk patterns produce different warning levels.
Zhiwei Zhang, Wenxuan Yuan, Xiaoyuan Cheng, Pouria Behnoudfar, Chuanqi Chen, Charlotte Moser, Yuta Tarumi, Jin-Long Wu 等 13 位作者
Koopman representations describe nonlinear dynamics through linear evolution in a transformed space, offering an attractive framework for their linear simplicity and generality. Yet these advantages do not necessarily translate into improved performance in deep latent data assimilation (LDA). We systematically compare seven representative methods and structural baselines across five systems spanning approximately periodic to strongly chaotic dynamics and a broad range of state dimensions. We evaluate forecast and assimilation accuracy, physical state recovery, latent-trajectory behavior, and dynamical consistency, and assess Gaussian error assumptions, objective convexity, and uniqueness of analysis solutions. Our results reveal a trade-off between representational flexibility and optimization tractability. Linear evolution of the latent state can stabilize short-term forecasts but restrict expressiveness in strongly chaotic and high-dimensional systems, without consistently improving assimilation accuracy. Parameterized linear operators offer greater flexibility, yet their joint optimization with the encoder--decoder remains nonconvex. Methods with closed-form analysis updates generally perform better and exhibit greater robustness in our experiments, although matrix inversion remains a computational bottleneck. These findings show that the practical benefits of Koopman structure depend on both sufficient observational information and the choice of assimilation procedure.
Xin Zhang, Yabo Chen, Yijie Fang, Wanying Qu, Haibin Huang, Chi Zhang, Feng Xu, Xuelong Li
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D conversion approaches often suffer from object interpenetration. Furthermore, physics-based scene-level 3D generation methods exhibit spatial misalignment, stylized artifacts, and inconsistencies with the input data, restricting their use in realistic interactive video synthesis. We propose PhysOmni, a training-free framework that converts a single image into a physically consistent and controllable video through holistic scene-level 3D reconstruction. By rep?resenting the full scene geometry in a unified spatial coordinate system, PhysOmni resolves object penetration and alignment ambiguity. Unlike prior methods, this formulation enables accurate scene?level multi-object interactions and introduces richer, complex control types for advanced mechanics?based manipulation. By decoupling simulation from rendering, PhysOmni bypasses latency-heavy priors, achieving real-time physical interaction previews paired while preserving photorealistic visual fidelity. Experimental results demonstrate that PhysOmni substantially outperforms prior methods in physical fidelity, spatial coherence, and controllability. Project Page: https://zephipage.github.io/PhysOmni/
A poor start lowers the ceiling, but does not negate the value of finishing well. In autoregressive video temporal grounding, models systematically exhibit an endpoint performance asymmetry, predicting ends significantly worse than starts. A committed flawed start acts as an immutable physical constraint, irreversibly capping the attainable overlap as a sunk loss. While models should minimize the remaining conditional regret, standard post-training paradigms fail to teach this adaptation. Specifically, teacher-forced SFT suffers from strict prefix exposure bias, and holistic trajectory evaluation in standard GRPO inadvertently penalizes conditionally optimal ends if they follow a poor start. To address this, we introduce FinishStrong, a novel two-stage post-training framework explicitly designed to teach optimal continuations. First, Online-start SFT exposes the end prediction to the model's own generated contexts. Second, Conditional-tree GRPO restructures the sampling topology, centering end rewards exclusively within the same-start branch to mathematically isolate the conditional end quality from the inherited start penalty. FinishStrong-9B achieves a state-of-the-art 61.7\% overall IoU on TimeLens-Bench, remarkably outperforming flagship closed-source models like Gemini-3.8-Flash and Qwen3.8-Max. Crucially, when forced to continue from imperfect starts, it reduces the subsequent end prediction error by 36.5\%, proving its exceptional ability to end well after flawed starts. Code will be open.
Streaming video question answering (QA) requires real-time reasoning over continuous video streams under strict latency and active-context budgets. Current streaming vision-language models (VLMs) often give confident yet ungrounded answers when queries are ambiguous or have false premises, or when relevant visual evidence is no longer in the active context. Proactive clarification can help, but must satisfy the same latency and memory constraints. We present StreamClarify, a training-free framework for grounded streaming QA that combines a pre-answer uncertainty check with hierarchical memory. The check uses the entropy of a binary pre-answer judgment as a lightweight uncertainty score to decide whether to answer directly or request clarification. To support re-answering, a temporal-pyramid KV cache maintains a bounded active visual context, while a CPU-side semantic retrieval archive provides access to historical frames. We further construct StreamClarify-QA, a diagnostic benchmark of 1,837 QA pairs from StreamBench and OVO-Bench, spanning standard, referential ambiguity, and unanswerable scenarios. Across three VLM backbones, StreamClarify improves Macro accuracy by up to 8.2 points over backbone-matched baselines. At comparable trigger rates, entropy-based selection achieves more than 18 points higher precision than random selection in identifying initially incorrect answers. Under oracle user guidance, clarification improves Macro accuracy by up to 3.5 points. We also report a controlled, oracle-assisted Qwen3-VL simulation on Ambiguous QA with generated questions and referent-only user replies, where the entropy-gated condition improves accuracy by 8.3 points.
Yiming Yan, Hongyang Wang, Wenbo Chen, Xuan Wang, Jingguo Liu, Xian Li, Chen Qi, Leo Fan 等 15 位作者
Agentic reinforcement learning (RL) often requires repeated tool calls in task-specific environments. A training job may create thousands of these environments in bursts while sharing a cluster with other jobs. We present Sandman, a sandbox service built and operated at Amazon for agent tool execution and evaluation. It serves multiple production agentic RL workloads on shared Kubernetes. A training framework supplies a task image and uses commands and file operations in the returned sandbox. Files and processes persist across calls until the framework releases the environment. Sandman manages creation, readiness and cleanup. Each sandbox is a Kubernetes pod with a small daemon mounted into the unmodified image. In a scale test, Sandman held 11,858 concurrent tiny sandboxes. Four production SWE-bench Verified training campaigns created 3.1 million sandboxes in October 2026. We report the design trade-offs and operational lessons from handling creation bursts, preparing task environments, reclaiming abandoned sandboxes, and running evaluation under controlled conditions. We will open-source Sandman's daemon, provider and pool.
Zhiqiang Wu, Shuang Sun, Jiale Zhang, Jing Li, Yibo Chen, Xu Tang, Yao Hu
Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of reference images increases. While supervised fine-tuning (SFT) can equip models with basic MICo ability, it provides only implicit supervision on the composed image and often fails to learn reliable object-level correspondence across multiple references. We propose DeCoRL, a reinforcement-learning (RL) framework that improves MICo consistency by decomposing holistic MICo consistency into object-level consistency. DeCoRL first establishes instruction-relevant object correspondences across reference images and localizes the corresponding regions in the generated image. It then uses a VLM-based reward model trained on single-object consistency annotations to produce fine-grained, object-wise feedback, which is aggregated into a multi-object consistency reward to guide RL post-training. We further introduce DeCo-Bench, a benchmark covering compositions from 2 to 6 reference images. Experiments on DeCo-Bench and the public MICo-Bench demonstrate consistent improvements in MICo consistency.
Lu Wang, Zhuoran Jin, Longxiang Wang, Junhong Chen, Yupu Hao, Yao Xu, Daojian Zeng, Yubo Chen 等 11 位作者
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to answer. However, existing proactive paradigms typically assume that the information required to answer a query is complete, leaving models to only wait or answer. In the real world, however, information is often incomplete due to uncertainty from either the video or the user. In proactive paradigms, such uncertainty can cause the model to wait forever or generate highly hallucinatory responses. We therefore argue that proactive interaction should be redefined with a third action: ask, allowing models to actively ask for missing information. To study when and what models should ask before answering, we introduce AskStream, the first multi-turn benchmark spanning video and user uncertainty for streaming video understanding, with four task categories and eight subtasks. It contains 438 videos with 2,714 manually annotated frame-level time windows across three types: wait, ask, and answer. Across both multiple-choice and open-ended settings, even the strongest model attains only 52.18% on our proposed Ask-F1 metric, highlighting substantial limitations in proactive information seeking under uncertainty.
Continuous visual world simulation requires coupling evolving scene geometry with temporally persistent appearance. We present UniWorld, a unified framework that integrates depth trajectories and reference appearance within a shared video generation model. The central design maintains visual and geometric histories on a common timeline. Noise-aligned overlapping continuation places generated history at the prescribed sampling noise level and commits only newly generated latents. Rolling depth latent state preserves the corresponding geometric controls, incrementally reads newly available geometry, and keeps the conditioning fixed within each sampling window. Together, these mechanisms ensure exact preservation of latent history while bounding the active depth state by the window size. We evaluate continuous generation, paired history interventions, and long-horizon behavior across diverse scene categories. The same generator supports estimated, native, and on-demand simulator depth, while cached and incremental execution paths produce bitwise-identical outputs. Appearance changes and geometric control branches operate through the same interface without modifying committed history. The measured steady-state DiT execution path achieves real-time generation throughput, demonstrating the efficiency of UniWorld for continuous visual world simulation. Project page: https://zephipage.github.io/UniWorld.
Kailai Feng, Haoxiang Rao, Yuxiang Wei, Bo Chen, Junsong Li, Yang Pan, Chengkun Cai, Jagmohan Chauhan
Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and server-side models. We introduce MoI-Bench, a benchmark grounded in mobile user needs, comprising 64 subtasks and 1150 samples. It defines 16 operations, such as removal and replacement, and eight visual target categories covering content such as portraits and text. These form two orthogonal axes whose applicable combinations define specific tasks, such as removing facial makeup. To better guide model improvement, we further propose MoI-Eval, which introduces task-specific criteria covering instruction following, visual quality and detail preservation. We further construct sample-level evaluation questions and aggregate their scores into overall quality and capability profiles along the operation, target and criteria axes. We evaluate representative on-device and server-side models and measure mobile deployment costs. Results show that this decoupled Operation x Target design provides finer-grained guidance for improving compact models. For example, it highlights the need to prioritize specific capability gaps (e.g., text-replacement) over broad application-level goals (e.g., improving text editing). Unlike conventional benchmarks that rank models using a single score, we introduce a two-dimensional Quality-Deployability capability map to assess models for practical mobile use. The map shows that current on-device models can achieve efficient generation or editing but expanding their task coverage deserves greater attention than further improving deployment efficiency. Further progress requires improving editing quality, particularly identity preservation and text rendering, while broadening task coverage.
This report presents the implementation and validation of two end-to-end multimodal adaptation pipelines for 3D-aware visual question answering on a custom spatial dataset. The first pipeline fine-tunes HiSpatial-3B, which augments RGB observations with metric-scale 3D point maps; the second adapts Qwen3-VL through memory-efficient QLoRA-based supervised fine-tuning. The completed engineering stack covers dataset conversion, image-annotation alignment, monocular geometry preprocessing, instruction construction, mixed-domain training, checkpoint management, batch inference, and automated evaluation. On the target spatial benchmark, HiSpatial adaptation increases overall accuracy from 1.73% before fine-tuning to 79.89% at 3,600 steps. On a separately collected styled split, accuracy improves from 14.9% to 55.1%, indicating transfer beyond the original training set. The Qwen3-VL pipeline is likewise implemented end-to-end for both 8B- and 32B-scale models using mixed-domain QLoRA adaptation. The resulting accuracy improves from 20.74% to 45.27% for Qwen3-VL-8B and from 30.79% to 47.60% for Qwen3-VL-32B. Together, these results establish two complementary and reproducible adaptation pipelines for geometry-aware and general-purpose multimodal spatial reasoning. These results establish a reproducible engineering foundation for subsequent work on metric 3D reasoning, spatial grounding, and domain-adapted multimodal systems, while also identifying training-data composition as a central factor in preserving general multimodal capability during specialization.
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.
Abhishek A. Sabnis, Mihai Mitrea, Lya Lugon, Karine Sartelet, Marc Bocquet, Xiaoyuan Cheng, Shupeng Zhu, Sibo Cheng
Full-field reconstruction of air pollution is essential for evaluating pollution exposure and supporting public health decision-making. However, the complex interactions among pollutants, hard-to-predict weather patterns, and limited monitoring station coverage make this a complex task. We apply deep learning techniques to provide fast and accurate reconstructions from sparse observations of four key pollutants: NO2, O3, PM2.5 and PM10. Models are trained on full-field simulation data and evaluated on real-world observations collected from 9 to 28 monitoring stations in the city of Paris. We introduce a diffusion-based generative framework for multi-pollutant reconstruction and benchmark its performance against deterministic deep learning models. Despite noisy observations and strong spatial variability, the models achieve high structural similarity on simulated validation data and produce realistic spatial patterns on real-world observations, as indicated by power-spectrum analysis. We introduce data augmentation methods that enable transfer to real-world observations without retraining, allowing the models to generalise beyond the training period. These findings highlight the potential of ML models for reliable real-world deployment in air pollution reconstruction tasks.
Zhuohang Li, Yiding Ma, Yu Shang, Lei Jin, Shengyuan Wang, Jianjie Fang, Zhaolu Wang, Xvyuan Liu 等 29 位作者
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The project page including codes and demos is available at: https://world-arena.ai/.
Microkernels provide good features such as high security, safety, and flexibility, but their reliance on hardware-based isolation leads to heavy performance overhead, limiting their widespread adoption. Although constructing single-address-space microkernels based on safe language-based isolation is a promising approach to addressing the performance issue, this approach still faces challenges in maintaining the principle of minimality and enforcing capability-based, fine-grained access control over system resources. We propose safeL4, an approach to constructing microkernels based on safe languages. It guarantees minimality through low-level abstractions for unsafe operations, and implements a capability system based on the safe language's object capabilities to achieve fine-grained access control over all operations on system resources. We implement a prototype system in Rust, and our evaluation results show that the primitives provided by safeL4 are, on average, 1.9$\times$ faster than those of seL4.
Recent studies have applied large language model (LLM) agent systems to computational simulation workflows. Such workflows are long-horizon, so the information generated can exceed what an LLM can reason over at once, its context window. Context management is therefore essential, yet existing systems have either neglected it or treated it as a supporting mechanism rather than a subject of study. This paper presents MarkovSim, an LLM agent harness for long-horizon computational simulation, whose core is a context management scheme built into the workflow. The workflow record is written to a memory system with a predefined schema, and at workflow-defined boundaries, namely the state transitions of a finite-state machine a compact representation of the solution progress is constructed from it as the agent's context. Instantiated on finite element analysis and evaluated on six benchmark problems, MarkovSim passed 16 of 18 runs and corrected its own faults in both the solver operations and the model physics. The engineer was consulted only where engineering judgement was needed. The context remained bounded throughout every run, regardless of its length.
Shanbo Cheng ByteDance Inc., Shuaijie She, Yu Bao ByteDance Research, Jianbing Zhang Nanjing University, Jiajun Chen, Shujian Huang Nanjing University
Large language models (LLMs) with long context windows offer the potential to translate entire documents in a single pass, yet they frequently suffer from catastrophic information distortion, undermining the strict faithfulness required for translation. This challenge is compounded by the scarcity of document-level parallel data, which makes both supervised fine-tuning and reliable evaluation prohibitively expensive. We propose LongDu, a self-supervised post-training framework that improves long-document translation reliability via round-trip consistency. Given monolingual documents, LongDu samples multiple candidate translations, back-translates each candidate, and optimizes the model to prefer translations that best reconstruct the source. To make this signal robust for long-form generation, we design a reward that filters trivial failure modes (e.g., copying and local language drift) before applying a reconstruction and fluency score, enabling stable reinforcement learning without human annotations. We additionally introduce Long-CIRT, an automatic evaluation protocol that quantifies information distortion by measuring how much a LLM’s performance degrades after a translation cycle. Across multiple base models, LongDu substantially improves information retention and translation quality, with gains that generalize beyond the training length range and to unseen target languages.
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
Tianyi Men , Institute of automation, Chinese academy of science, Zhuoran Jin, Pengfei Cao Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Yubo Chen Minzu University of China, Kang Liu Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Jun Zhao Institute of automation, Chinese academy of science
Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open-source MLLMs are cost-efficient and privacy-preserving compared with commercial large models, they suffer from weak planning and limited cross-website generalization. To address these limitations, we introduce the planning experience exploration and utilization (PEEU) method, which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high-level training data. To quantitatively analyze the generalization behaviors driving this performance, we propose the task decomposition hierarchical analysis framework (TDHAF) to systematically study compositional generalization across three task granularities: low, middle and high levels. Our analysis reveals that mastering low-level atomic skills does not guarantee high-level planning competence, while high-level task training yields stronger OOD generalization. Experiments on real-world benchmarks demonstrate PEEU’s superior effectiveness: our 7B model achieves 30.6% accuracy, outperforming the much larger Qwen2.5-VL-32B model. These demonstrate constructing hindsight high-level tasks and leveraging experiences is crucial for OOD planning abilities of small MLLMs.
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
Dongqi Huang, Tong Zhou Du Xiaoman Technology (Beijing) Co., Ltd., Zhuoran Jin, Shenghui Shi Beijing University of Chemical Technology, Maoyujiao, Kang Liu Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Jun Zhao Institute of automation, Chinese academy of science, Yubo Chen Minzu University of China
Explainable diagnosis requires that authoritative medical knowledge provide the rationales linking a patient’s clinical manifestations to the diagnostic conclusion. Although large language models (LLMs) hold great potential to facilitate explainable diagnosis, their effectiveness is often constrained by insufficient diagnostic expertise. To address this limitation, we propose Self-learned Explainable Knowledge Augmented Diagnosis (SEKAD), a unified LLM-based framework for faithful and explainable diagnosis. Our approach builds a high-quality diagnostic knowledge base through a record-driven explanation learning paradigm, as well as applies this knowledge via an explanation-based diagnostic process that ensures faithful inference. Experiments on the DiReCT and JAMA benchmarks show that SEKAD consistently outperforms strong baselines across the metrics. In particular, on the DiReCT benchmark, SEKAD improves the explanation completeness metric from 64.5% to 76.9% over the best existing methods, highlighting its effectiveness in enhancing diagnostic explainability and showing that our text mining approach produces knowledge that is both reliable in quality and large in quantity.
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
Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Pengfei Cao Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Yubo Chen Minzu University of China, Kang Liu Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Jun Zhao Institute of automation, Chinese academy of science
Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key question: What can multimodal Chain-of-Thought reasoning do, and where and why does it fall short? To this end, we evaluate 12 multimodal tasks across perception and reasoning categories using both 14 non-reasoning models and 8 reasoning models. Our analysis reveals several important findings: (1) CoT is not a free lunch and should be used selectively depending on the specific requirements of each task. For perception tasks, CoT can lead to undesirable side effects, such as reduced performance in visual grounding and object counting. In contrast, it proves effective for reasoning tasks involving mathematical, scientific, and multi-image reasoning; (2) Compared to original models, existing open-source multimodal reasoning models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities; (3) Visual reasoning remains a key bottleneck for current multimodal CoT, as models exhibit a Look Light, Think Heavy” pattern where verbal reflection rises and falls during reasoning, whereas visual reflection consistently diminishes. These findings suggest that while multimodal CoT handles verbal reflection relatively well, it lacks the ability to maintain deep visual introspection throughout the reasoning process.
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
Wenbo Chen Amazon, Veena Padmanabhan Amazon, Tootiya Giyahchi Amazon, Elaine Wong Amazon, Leman Akoglu Amazon and Carnegie Mellon University
Hallucination, broadly referring to unfaithful, fabricated, or inconsistent content generated by LLMs, has wide-ranging implications. Therefore, a large body of effort has been devoted to detecting LLM hallucinations, as well as designing benchmark datasets for evaluating these detectors. In this work, we first establish a desiderata of properties for hallucination detection benchmarks (HDBs) to exhibit for effective evaluation. A critical look at existing HDBs through the lens of our desiderata reveals that none of them exhibits all the properties. We identify two largest gaps: (1) RAG-based grounded benchmarks with long context are severely lacking (partly because length impedes human annotation); and (2) Existing benchmarks do not make available realistic label noise for stress-testing detectors although real-world use-cases often grapple with label noise due to human or automated/weak annotation. To close these gaps, we build and open-source a new RAG-based HDB called TRIVIA+ that underwent a rigorous human annotation process. Notably, our benchmark exhibits all desirable properties including (1) TRIVIA+ contains samples with the longest context in the literature; and (2) we design and share three sets of noisy labels with different, sample-dependent noise schemes. Finally, we perform experiments on RAG-based HDBs, including our TRIVIA+, using popular SOTA detectors that reveal new insights: (i) ample room remains for current detectors to reach the performance ceiling on RAG-based HDBs, (ii) the basic LLM-as-a-Judge baseline performs competitively, and (iii) label noise hinders detection performance. We expect that our findings, along with our proposed benchmark, will motivate and foster needed research on hallucination detection for RAG-based tasks.
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