跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-07 21:46 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-06 21:51 — 2026-11-07 21:51（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-07 21:46最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 23 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-07 21:41（北京时间）
新论文 · v1arXiv:2611.07739

Fix One, Miss Another: Leveraging Historical Bug Fixes to Uncover Residual Bugs in Database Systems

Yankai Rong, Zhaoyang Zhang, Shuang Liu, Wei Lu, Xiaoyong Du

原文摘要

Database management systems (DBMSs) implement SQL constructs through grammar-driven dispatch handlers. Although handlers for syntactic siblings implement different SQL constructs, they often share a common implementation pattern, including argument extraction, type checking, and permission validation. Consequently, a bug fix that hardens the handler exercised by a historical bug may leave the corresponding logic in sibling handlers vulnerable to the same semantic flaw. We refer to such defects as sibling bugs. Despite the structural similarity among sibling handlers, existing bug-finding techniques rarely exploit historical fixes to systematically uncover these related defects. We present Reaper, a novel approach for detecting sibling bugs guided by historical bug fixes. Reaper first analyzes a bug fix to infer a trigger profile, which characterizes the conditions under which the defect is exposed, and a validation profile, which captures the semantic evidence needed to distinguish buggy behavior from correct behavior. It then projects the trigger profile onto syntactic siblings through grammar-guided test mutation, generating tests that exercise corresponding semantic paths in sibling handlers. Finally, Reaper validates suspicious behaviors using the inferred validation profile through a staged validation process, reducing false positives caused by complex DBMS behavior. We evaluate Reaper on four widely used DBMSs, including MariaDB, MySQL, OceanBase, and CockroachDB. Reaper uncovers 61 previously unknown bugs, of which 57 have been confirmed by developers and 13 have been fixed at the time of writing. These results demonstrate that historical bug fixes contain actionable semantic knowledge that can be systematically transferred across syntactic siblings to uncover otherwise overlooked defects.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.26092

Hybrid Dual-Batch and Cyclic Progressive Learning for Efficient Distributed Training of Convolutional Neural Networks

Kuan-Wei Lu, Ding-Yong Hong, Pangfeng Liu, Jan-Jan Wu

原文摘要

Distributed deep learning is critical for training convolutional neural network (CNN) models on large-scale image datasets with numerous parameters. Current research primarily focuses on leveraging additional hardware resources and powerful computing units to accelerate the training process. As a result, larger batch sizes are often employed to speed up training. However, training with large batch sizes can lead to lower accuracy due to poor generalization. To address this issue, we propose the dual-batch learning scheme, a distributed training method built on the parameter server framework. This approach maximizes training efficiency by utilizing the largest batch size that the hardware can support while incorporating a smaller batch size to enhance model generalization. By using two different batch sizes simultaneously, this method improves accuracy with minimal additional training time. Additionally, to mitigate the time overhead caused by dual-batch learning, we propose the cyclic progressive learning scheme. This technique repeatedly and gradually increases image resolution from low to high during training, thereby reducing training time. By combining cyclic progressive learning with dual-batch learning, our hybrid approach improves both model generalization and training efficiency for image classification tasks. Experimental results with ResNet-18 demonstrate that, compared to conventional training methods, our approach improves accuracy by 3.3% while reducing training time by 10.1% on CIFAR-100, and further achieves a 34.7% reduction in training time on ImageNet.

cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07541

CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal Transition On-Policy Self-Distillation

Ying Li, Yongle Cheng, Jing Li, Xingquan Cai, Yawei Luo

原文摘要

Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet existing benchmarks mainly focus on static scene understanding. When objects are moved or swapped, models must infer not only spatial relations but also how interventions change the scene state. To address this problem, we introduce CST-Bench, a benchmark for counterfactual spatial reasoning. CST-Bench contains 7,082 examples covering 6 intervention types and 12 transformation operators, with dense causal annotations including intervention sources, affected relations, expected effects, invariant relations, and metric changes. We benchmark general-purpose MLLMs on CST-Bench and further compare post-training strategies on CST-Bench and standard spatial benchmarks. Results show that methods effective for ordinary spatial reasoning can still fail under counterfactual interventions. We further formulate counterfactual spatial reasoning as causal state-transition modeling and propose CT-OPSD, which uses CST-Bench annotations to guide a teacher model in learning counterfactual state transitions and causal reasoning chains. These chains are then distilled into a student model that reasons only from real observations. Overall, experiment results establish CST-Bench as a challenging benchmark and reusable supervision resource for counterfactual spatial reasoning. CT-OPSD further provides an initial demonstration of how its annotations can support model improvement.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07515

LMGN: A Unified Policy Learning Model for Last-Mile Grasp-Navigation

Xuenmin Hu, Qingxue Qian, Wei Luo, Benyi Ma, Bo Tang, Long Chen

原文摘要

Legged robots equipped with manipulators have shown significant potential in the fields of daily life and industry in complex environments. However, existing methods mainly focus on global navigation or manipulation independently, while overlooking the last-mile navigation problem, where the robot must jointly determine the base placement, approach direction, and grasp execution to achieve reliable object grasping, and different manipulation stages require distinct control behaviors. To address these challenges, we propose Last-Mile Grasp-Navigation (LMGN), a unified policy learning model for Quadruped robot loco-manipulation. An Explicit Distance and Directional Reachability (ED-DR) representation is first introduced to explicitly represent the features of grasp-compatible base placement and approach direction. We then develop a semantically aligned Hierarchical Mixture-of-Experts (HMoE) policy that models stage-aware behaviors across the stages of base adjustment, pre-grasp alignment and grasp execution, and object lift. Finally, a new optimization method that jointly aligns navigation and manipulation, stage-dependent expert routing, and action-level consistency is proposed to optimize the HMoE policy. Extensive experiments on the Habitat and Isaac Gym simulators demonstrate that LMGN consistently outperforms state-of-the-art methods, denoting that integrating grasp-aware reachability with stage-aware policy learning significantly improves the success rates of last-mile navigation and target grasp for robots.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06918

从像素到动作：迈向原生视觉-语言-动作策略

From Pixels to Actions - Towards Native Vision-Language-Action Policies

Weichen Fan, Haiwen Diao, Penghao Wu, Siyuan Hu, Ziqi Huang, Tianqi Liu, Mingze Sun, Ziyi Wang 等 17 位作者

AI 速读 基于摘要

提出无视觉编码器的 NEO-VLA 框架，让动作策略直接访问随语言共同演化的多层视觉表示，而非固定编码器输出。

cs.CV

arXiv ↗PDF ↗
查看原文摘要

Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle state changes. This raises a fundamental question: should action policies inherit a fixed visual endpoint, or directly access evolving visual computation? We introduce NEO-VLA, a structurally encoder-free vision-language-action framework. Images are tokenized by lightweight patch convolutional layers and evolve jointly with language throughout the backbone, allowing a flow-matching action expert to draw from instruction-conditioned visual representations at different depths. This simple change reveals a consistent pattern. Native architectures outperform encoder-based counterparts under controlled comparisons; full fine-tuning reduces but does not erase the gap, and additional scale alone cannot recover it. More strikingly, layer-wise probing shows that the action-critical signals often peak well before the final visual representation. Across diverse manipulation settings and distribution shifts, NEO-VLA consequently achieves stronger and more robust control. Together, these results suggest that embodied control benefits from access to visual representations across the computational hierarchy, rather than a fixed encoder output.

新论文 · v1arXiv:2611.06741

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

Ruikang Li, Zixuan Chen, Jiarui Wu, Mingde Yao, Yiyuan Zhang, Yujin Wang, Hanming Deng, Lewei Lu 等 9 位作者

原文摘要

Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering pretrained priors, or through specialized inference-time mechanisms that are difficult to scale to foundation models. We introduce TailSteer, a final-stage training framework that improves multi-turn robustness while retaining the generative and editing capabilities acquired through earlier training. TailSteer follows a simple principle: keep early denoising dynamics close to those of the base model and concentrate preservation corrections near the trajectory tail, where fine-grained deviations can be suppressed. These corrections are learned from the editor's own on-policy denoising rollouts, using unchanged source content as a preservation reference without requiring curated ground-truth editing pairs. Experiments across the FLUX, SenseNova, and Qwen families show that TailSteer substantially reduces cumulative drift over 15-20 editing turns while largely preserving base-model performance on extensive text-to-image and single-image editing benchmarks. These results demonstrate that long-horizon editing robustness can be unlocked in foundation models after TailSteer, rather than by relearning their existing capabilities.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.34249

Evolving Support Priorities in Empathetic Reinforcement Learning

Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen, Sirui Chen, Lewei Lu, Beier Zhu 等 9 位作者

原文摘要

We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve. Code is available at https://asa13opp.github.io/CARE-project-page.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01560

让机器人使用智能体走向大众：一个配开放模型的统一测试框架

Democratizing Robot-Use Agents: A Unified Harness with Open Models

Jiarui Yuan, Yuxin Zuo, Xiaoyu Huang, Wenbo Zhang, Kwanyoung Park, Junlin Yang, Tianxiang Zhang, Ruoqu Chen 等 28 位作者

AI 速读 基于摘要

作者提出统一测试框架 uni-robot-agent，使开放权重模型可开展机器人使用智能体研究并支持后续训练，报告开箱即用的 Qwen3.8-Flash-Next 在 RoboDojo 上取得 31.39 分。

cs.RO

arXiv ↗PDF ↗
查看原文摘要

Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize RUA research, we introduce uni-robot-agent, a unified harness for competitive open-weight robot use that supports further training. Without privileged inputs, an out-of-the-box Qwen3.8-Flash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.

版本更新 · v2arXiv:2609.23540

Vector Balancing in Polynomial Time

Shengtao Guo, Ethan X. Fang, Junwei Lu

原文摘要

The Komlós problem asks for signs $\varepsilon\in\{-1,1\}^n$ with $\|A\varepsilon\|_\infty$ bounded by an absolute constant whenever the columns of $A\in\mathbb R^{m\times n}$ have Euclidean norm at most $1$. We give the first polynomial-time algorithm for this problem in the unit-cost real-RAM model. Our deterministic algorithm achieves discrepancy at most $8272$. As a consequence, we obtain a deterministic $O(\sqrt t)$-discrepancy algorithm for the Beck-Fiala problem on set systems in which each element belongs to at most $t$ sets. Our algorithm rounds a fractional coloring while keeping the row sums bounded. Its key idea is to keep the number of nearly tight row constraints small relative to the number of active coordinates. We achieve this through a spectral bound based on a weighted Gram matrix of squared row entries. We maintain the bound using a cubic spectral potential and negative-curvature updates that satisfy the required linear constraints.

cs.DS · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04689

Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation

Jinwu Hu, Langyu Bian, Jian Sun, Dongjin Yang, Chao Shuai, Yufeng Wang, Kai Zhou, Bin Xiao 等 11 位作者

原文摘要

Open-set test-time adaptation (TTA) aims to adapt source-trained models to unlabeled test streams where covariate-shifted in-distribution (csID) samples and covariate-shifted out-of-distribution (csOOD) samples may coexist. Existing TTA methods are typically designed under a closed-set assumption and therefore lack explicit mechanisms for reliably distinguishing csID from csOOD samples. Consequently, csOOD samples may be mistakenly included in confidence-enhancing adaptation, producing harmful gradients that degrade known-class performance. To address this, we propose Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation (UAPA), a plug-and-play method for reliable open-set adaptation. Specifically, we first introduce Uncertainty-Driven ID/OOD Separation, which combines a classifier-prototype score with a mini-batch-normalized evidence-derived uncertainty score to distinguish csID from csOOD samples. We then propose a Dynamic Prototype Refinement strategy that periodically refines class-specific target prototypes using buffered csID features to progressively follow the estimated class directions. Lastly, we introduce Contrastive Prototype Entropy Adaptation, which applies entropy minimization to csID samples and entropy maximization to csOOD samples, while prototype-level contrastive learning aligns csID features with their corresponding target prototypes and reduces the maximum similarity between csOOD features and known-class prototypes. Empirically, UAPA outperforms the strongest baselines on the CIFAR benchmarks and Tiny-ImageNet-C, improving average OSCR by 2.08 and 1.28 percentage points, respectively.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.09981

Optimal Value Inference for Reinforcement Learning

Nan Lu, Ethan Lee, Ruicheng Ao, David Simchi-Levi, Junwei Lu

原文摘要

We study offline inference for the optimal value in reinforcement learning under finite state and action spaces. Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which we approximate the maximum Bellman operator by its softmax correspondence. We propose a debiased estimator through the Neyman orthogonality and establish its asymptotic normality under diverging horizons even when the behavior policy changes with time, as long as the nuisances have the statistical rates that can be achieved by many machine learning methods. We provide a concrete estimating procedure for these nuisances and show they can lead to valid inference. Synthetic experiments validate the numerical performance of our inference method, and we implement it in real-life decision-making problems, including bike repositioning and AI agentic tool use.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.19009

Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning

Linwei Dong, Ruoyu Guo, Ge Bai, Quan Zheng, Yawei Luo, Changqing Zou

原文摘要

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation offers potential, a naive fusion of these two objectives relies on suboptimal raw sample evaluation. This sample-based scoring creates inherent conflicts with the distillation trajectory and produces unreliable rewards due to the noisy nature of early-stage generation. To overcome these limitations, we propose GDMD, a novel framework that redefines the reward mechanism by prioritizing distillation gradients over raw pixel outputs as the primary signal for optimization. By reinterpreting the DMD gradients as implicit target tensors, our framework enables existing reward models to directly evaluate the quality of distillation updates. This gradient-level guidance functions as an adaptive weighting that synchronizes the RL policy with the distillation objective, effectively neutralizing optimization divergence. Empirical results show that GDMD sets a new SOTA for few-step generation. Specifically, our 4-step models outperform the quality of their multi-step teacher and substantially exceed previous DMDR results in GenEval and human-preference metrics, exhibiting strong scalability potential.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11500

Learning qBIC Resonances across Metasurface Families in Dielectric Fourier Space

Shuangteng Lei, Li Yu, Tianxin Li, Wei Lu

原文摘要

Bound states in the continuum (BIC) metasurfaces are typically described by geometry-specific parameters, hindering cross-geometry comparison, while ultranarrow quasi-BIC (qBIC) features are easily diluted in full-spectrum learning. Here, we map 2,015 samples from seven dielectric metasurface families onto a shared reciprocal-lattice grid. Two fixed low-order Fourier descriptors capture within-branch resonance shifts, with mean $R^2$ values of 0.871-0.999. Field-level analysis of two representative branches shows that these shifts are consistent with the Maxwell-Fourier perturbation picture. A five-channel Fourier-space backbone models the broadband spectrum. A local resonance expert uses complex Fourier coefficients to parameterize the qBIC resonance through a differentiable Fano layer. The expert reduces resonance-position mean absolute error (MAE) from 3.2 to 0.95 nm and reduces the minimum-transmission MAE by a factor of 14 on a geometry-blocked test set. The same coordinate supports spectrum-to-structure reconstruction.

physics.optics · cs.LG · physics.comp-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02794

SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping

Haoyuan Wang, Shuai Peng, Yongkai Liao, Yuxiao Sun, Wei Luo, Xinxing Chen, Jian Huang

原文摘要

Robust multimodal perception for soft robotic grasping is challenged by modality-dependent noise, semantic ambiguity, and limited coordinated multisensory data. We introduce Soma, a dataset containing 100 objects, 1,000 continuous grasping trajectories, and 74,914 multimodal samples grouped by software acquisition cycle, spanning remote RGB, hand RGB, depth, tactile, IMU, and structured text observations. We also collect Soma-Success, an independent grasp-outcome dataset with 1,000 trials (998 retained after quality control), to evaluate frozen-encoder transfer for post-hoc grasp outcome classification and early grasp success prediction. Built on Soma, SomaAlign learns multimodal representations in three stages: masked reconstruction estimates relative modality reliability; reliability-aware contrastive alignment uses pair-specific adaptive temperatures to adjust alignment sharpness; and conflict-aware semantic constraints improve intra-sample cross-modal consistency while preserving global feature geometry. SomaAlign achieves an average Recall@10 of 90.66% across 30 directed cross-modal retrieval tasks. The learned representations also support physical attribute recognition, multimodal question answering, cross-modal generation, and cross-dataset transfer to grasp outcome prediction. On Soma-Success, frozen SomaAlign encoders with lightweight probes achieve 94.59% post-hoc classification accuracy and 84.07% early prediction accuracy. Together, Soma, Soma-Success, and SomaAlign provide a data and representation-learning foundation for robust and transferable multimodal perception in soft robotic manipulation.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33259

RadonBench: A Benchmark of Classical and Learning-Guided Search Techniques for Problems in Combinatorial Geometry

Xiaoan Xu, Jesus A. De Loera, Ethan X. Fang, Junwei Lu, Luze Xu

原文摘要

Classical optimization and learning-guided search offer complementary approaches to open problems in discrete mathematics, but their outputs are difficult to compare when search spaces, validity checks, and stopping rules differ. We present \emph{RadonBench}, a benchmark for constructing maximum-cardinality Radon-free lattice configurations: finite subsets of $\mathbb{Z}^d$ admitting no integral Radon partition. It remains open whether Radon-free configurations with $11$ points in $\mathbb{Z}^3$ or $21$ points in $\mathbb{Z}^4$ are possible. If they exist, they would improve the corresponding lower bounds on the integer Radon numbers. We compare exhaustive extension, greedy local search, PatternBoost, AlphaZero, and AlphaEvolve. All outputs use one success predicate: a convex target-sized configuration succeeds exactly when its number of integral Radon points is zero. PatternBoost and AlphaZero construct verified Radon-free configurations of sizes $10$ and $20$, one point short of the respective targets; AlphaZero's best convex target terminals have two integral Radon points in both dimensions. Exhaustive extension over fixed seeds and declared finite search boxes likewise reaches a minimum of two integral Radon points. Greedy local search and AlphaEvolve each produce target-sized near misses with one integral Radon point. No audited run reaches zero. These results establish reproducible near-miss baselines over explicitly scoped search domains.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.22402

Reinforcement learning to improve large language model-based automated code compliance systems

Jack Wei Lun Shi, Minghao Dang, Wawan Solihin, Justin K. W. Yeoh

原文摘要

Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed by Group Relative Policy Optimization (GRPO) to improve the accuracy of the generated intermediate representations in the form of high-level code skeletons. The framework achieved final reductions of up to 21.3% and 41.0% in tree edit distance and token-level Levenshtein distance respectively, relative to the SFT baselines. Comparative analysis demonstrates that this approach in a zero-shot setting outperforms leading LLMs in both code structure and semantics, evaluated via few-shot prompting. Additionally, the GRPO stage produced a statistically significant reduction in false positives. By combining SFT with GRPO to optimize directly for domain-specific objectives, this approach offers a path toward more accurate and reliable LLM-based ACC systems.

cs.SE · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.08351

Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations

Zhiliang Chen, Alfred Wei Lun Leong, Shao Yong Ong, Apivich Hemachandra, Gregory Kang Ruey Lau, Chuan-Sheng Foo, Zhengyuan Liu, Nancy F. Chen 等 9 位作者

原文摘要

Fine-tuning an LLM to maximize performance on a downstream task requires finding the optimal data and model configuration. This is a black-box optimization problem that Bayesian optimization (BO) addresses by sequentially evaluating training configurations and using observed performance feedback to adaptively guide the search towards better configurations. However, directly applying BO to the joint data-model space suffers from two fundamental challenges: the prohibitive cost of full LLM training at each iteration, and the large number of BO iterations required for effective exploration due to the high problem dimensionality. This paper introduces JoBS, a BO-based approach that co-optimizes data and model configurations without requiring a full training run at every iteration. JoBS allocates an initial portion of the optimization budget to learn a scaling-law-inspired performance predictor that estimates fully trained LLM performance from only a small number of training steps. The remaining budget is then used to run BO with this predictor, eliminating the need for full training runs and enabling JoBS to explore significantly more data and model configurations within the same budget. We analyze JoBS's average regret and derive the optimal budget allocation between predictor learning and BO iterations. Empirically, JoBS outperforms independent data and model optimization methods and existing multi-fidelity BO baselines across a diverse set of downstream tasks. Our code is available at https://github.com/chenzhiliang94/BO-for-LLMs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.19846

HiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants

Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen 等 11 位作者

原文摘要

Long-horizon agentic systems become long-context systems by accumulation rather than through a single long document, since every step reassembles a prompt from role instructions, tool and sub-agent descriptions, recalled memories, dialogue history, and previous tool outputs, separately for every agent. This paper studies how such accumulated context can be trained, evaluated, and managed in hierarchical multi-agent assistants. We present HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, of which 17.7K carry memory entries in context, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcement learning. Building upon it, HiMA-R1 keeps the context budget of a trajectory under control through Variance-Reduction Group Relative Policy Optimization (VR-GRPO), which samples along an initial trajectory so that sampling cost grows additively with trajectory length and updates the agents with the largest reward variance, together with an efficiency reward on trajectory length and a memory evolution mechanism that repurposes GRPO rewards as cost-free signals for what stays in context. Agents built upon 3B and 7B open-source models match DeepSeek-R1 and surpass DeepSeek-V3 by 6.0 points on average, while reward-driven memory reduces the update steps needed for convergence by roughly 55%.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35316

RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization

Jiawei Lu, Chen Zhang, Jinwei Lu, Yuanwei Song, Yuanfeng Song, Raymond Chi-Wing Wong

原文摘要

Users often request charts without knowing which database or table holds the relevant data. Such requests may be ambiguous, and users may ask follow-up questions to deepen their analysis or iteratively refine existing charts. A useful assistant must therefore discover relevant data sources among heterogeneous databases, ask clarifying questions when needed, and track evolving user intent while preserving constraints established in earlier turns. Yet recent text-to-visualization agents typically rely on static agent harnesses that are predefined and remain unchanged despite recurring failures across tasks. To address this limitation, we introduce RSIV-Harness, which keeps the language model weights fixed and applies Recursive Self-Improvement to revise the surrounding harness from the agent's own failure traces. To balance flexible self-improvement with stability, we introduce a four-layer framework that evaluates proposed harness revisions through anchor and memory checks, refining those that pass and restoring the best validated harness otherwise. We further introduce ODAC-Vis, a benchmark with 640 tasks for Open-Domain, Ambiguous, and Conversational text-to-visualization that jointly evaluates open-domain data discovery, ambiguity resolution, multi-turn visualization refinement, and executable chart generation. Experiments show that a single round of RSIV-Harness improves all six evaluation metrics relative to the seed harness, with particularly large gains in executability (+28.02 points) and chart structure (+34.01 points), demonstrating the ability to learn from task-solving experience and turn recurring failures across tasks into substantial performance improvements.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34532

Multi-view Semantic-aware Resource Allocation for Edge AI

Jiawei Luo, Hussein Saleh, Mohamad Assaad

原文摘要

Semantic communication is emerging as a pivotal paradigm to overcome wireless resource scarcity in 6G networks. This paper proposes a novel end-to-end framework for semantics-aware resource allocation in multi-user Edge AI. We extend the Opportunistic Information Bottleneck (OIB) to a multi-view setting, termed the Multi-view Gaussian Information Bottleneck (MGIB), by fusing complementary source views without variational approximation or network retraining. A resource allocation framework is then formulated for joint compression-level selection, transmission mode selection (i.e., the number of active sources per group), and PRB assignment. The problem is formulated as a Mixed-Integer Linear Program (MILP), solved efficiently via a proposed Lagrangian Relaxation (LR) algorithm, and benchmarked against the NP-hard optimal solution. Simulations demonstrate that the proposed LR scheme achieves near-optimal utility, and doubles PRB efficiency versus average allocation.

cs.IT · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1309ACL Anthology · ACL 2026

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming

Jiwei Tang, Shilei Liu, Zhicheng Zhang, Qingsong Lv, Runsong Zhao, Tingwei Lu, Langming Liu Alibaba Group, Haibin Chen 等 12 位作者

原文摘要

Large Language Models (LLMs) demonstrate exceptional capability across diverse tasks. However, their deployment in long-context scenarios is hindered by two challenges: computational inefficiency and redundant information. We propose RAM (Read As HuMan), a context compression framework that adopts an adaptive hybrid reading strategy, to address these challenges. Inspired by human reading behavior (i.e., close reading important content while skimming less relevant content), RAM partitions the context into segments and encodes them with the input query in parallel. High-relevance segments are fully retained (close reading), while low-relevance ones are query-guided compressed into compact summary vectors (skimming). Both explicit textual segments and implicit summary vectors are concatenated and fed into decoder to achieve both superior performance and natural language format interpretability. To refine the decision boundary between close reading and skimming, we further introduce a contrastive learning objective based on positive and negative query–segment pairs. Experiments demonstrate that RAM outperforms existing baselines on multiple question answering and summarization benchmarks across two backbones, while delivering up to a 12x end-to-end speedup on long inputs (average length 16K; maximum length 32K).

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1324ACL Anthology · ACL 2026

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment

Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye Northeastern University, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai Tsinghua University, Tsinghua University 等 11 位作者

原文摘要

Large Language Models (LLMs) have achieved remarkable performance across a wide range of Natural Language Processing (NLP) tasks. However, in long-context scenarios, they face two challenges: high computational cost and information redundancy. To address these challenges, we propose GMSA, an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks. GMSA introduces Group Merging to achieve more uniform aggregation, mitigating semantic dominance during autoencoder pretraining, and Layer Semantic Alignment (LSA) to bridge the semantic gap between high-level abstract semantics and low-level input semantics. We first pretrain GMSA as an autoencoder and then fine-tune it for downstream tasks. Experiments demonstrate that GMSA improves context reconstruction compared to existing soft prompt compression paradigm and outperforms baselines on multiple long-context question answering and summarization benchmarks across two backbone models, while maintaining low end-to-end latency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.518ACL Anthology · ACL 2026

Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring

Xin Shi, Chao Zhang, Yifan Zhu, Xueqiao Zhang, Yawei Luo Zhejiang University

原文摘要

The development of LLM-based tutor agents faces challenges in simultaneously ensuring adherence to pedagogical principles and achieving optimal pedagogical effectiveness, particularly in dynamic, multi-turn interactions. Existing methods are often constrained by static data or sparse reward signals in online settings. To address this gap, we propose \textbf{M}ulti-\textbf{H}orizon \textbf{P}reference \textbf{O}ptimization (\textbf{MHPO}), a novel framework that iteratively refines tutor agents using a multi-horizon reward function within a dynamic teacher-student simulation environment. Specifically, this reward function is designed to capture both turn-level pedagogical quality and trajectory-level pedagogical effectiveness, which is estimated via Monte Carlo rollouts. We further investigate two distinct strategies to aggregate these rewards for policy optimization. Our experiments demonstrate that MHPO significantly enhances base model performance, achieving a superior balance between principles and effectiveness compared to various baselines.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表