Action
-
Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies
2026-11-10 12:04:54Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert StahlbockAbstract
Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13966
PDF
-
ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
Abstract
AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provisions and violate computer security laws. In this paper, we introduce ScrapeBench, the first agentic benchmark for empirically evaluating the legal compliance of AI agents with website scraping policies, namely terms of service (ToS) and $\texttt{this http URL}$ directives. Across widely used closed-weight and open-weight AI agents, we find that most agents exhibit low compliance rates (< 5%) when instructed to scrape websites in our sample of 1,626 popular websites that explicitly prohibit scraping. In addition, we observe that even where AI agents actively check the applicable ToS and $\texttt{this http URL}$, they continue to exhibit low compliance rates. Conversely, in our sample of 269 websites that do not prohibit scraping, we observe that agents sometimes refuse to scrape despite it being lawful, such as Claude Opus 4.6 exhibiting an over-refusal rate of 98.5%. Our human baseline experiments (n = 180 participants) suggest that humans exhibit compliance rates comparable to AI agents but over-refuse at much higher rates.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11306
PDF
-
FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders
2026-11-10 11:21:43Ziwei Wu, Jingrui HeAbstract
Large language model (LLM) recommenders can produce semantically different recommendations when a user's protected attribute changes, even if the interaction history remains fixed. Controlling this disparity is challenging when model weights and full-vocabulary logits are inaccessible. We propose FAIDER (Fairness-Aware Item-level DEcoding for Recommendation), which incorporates fairness into list construction by selecting complete item candidates rather than manipulating token-level logits or repeatedly repairing finished outputs. The central idea is to separate the operational criterion for a violation from how strongly generation is constrained. Conformal-inspired empirical calibration fixes a cross-group semantic-disparity threshold, while online decoding applies either hard filtering or a soft penalty adjusted through dual-inspired feedback to target a prescribed violation rate. Separately, we establish a pathwise guarantee: under a uniform enforceability assumption, the soft decoder's empirical violation rate exceeds its target by at most $O(1/T)$. Experiments across recommendation benchmarks and LLM backbones show that Soft FAIDER improves both measured semantic fairness and ranking quality over the evaluated prompt-repair baselines. It also generally achieves a more favorable fairness-utility balance than the hard variant, indicating that stricter per-recommendation constraints do not necessarily yield lower measured disparity.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10285
PDF
-
ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads
2026-11-10 11:18:34Xianghui Wang, Aoran Fu, Liyou Luo, Shanze Wang, Xiaoyu Shen, Dan Zhang, Wei ZhangAbstract
In recent years, humanoid loco-manipulation has progressed to whole-body grasping, lifting, and transport. A basic requirement underlying these tasks is carrying the object to its destination, which depends on the locomotion controller accurately executing velocity commands from the navigation policy. However, carrying an object in one hand introduces a persistent asymmetric upper-body load that can degrade velocity tracking. Persistent tracking biases can accumulate into position and heading deviations, increasing the risk of collisions and navigation failure. To address this problem, we present ReACT, a framework for accurate velocity tracking under asymmetric upper-body loads. Reflection-consistent disturbance modulation uses the estimated wrench to modulate actor features for load compensation while preserving action correspondence under reflected observations. Cross-load tracking consistency training compares loaded and unloaded conditions under the same velocity commands to promote consistent velocity tracking across loading conditions. Simulation experiments on a Unitree G1 humanoid robot show improved velocity tracking and reduced directional bias under varying asymmetric loads. Real-world experiments demonstrate collision-free goal reaching in all 40 tested navigation trials under unilateral hand loads with a fixed mapless navigation policy.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13929
PDF
-
From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations
2026-11-10 11:05:19Vojtech Cahlik, Amir Reza Mohammadi, Rodrigo Alves, Pavel Kordik, Eva ZangerleAbstract
Recommender systems increasingly influence what users discover and consume online, yet the decision logic behind their outputs often remains opaque. Counterfactual explanation (CFX) methods provide an effective way to show which changes to a user's interaction history would alter a recommendation. In recommendation settings, however, CFXs often require many edits, producing long, low-level lists that are hard for users to interpret. Moreover, most evaluations emphasize edit counts while largely overlooking whether the resulting CFXs are coherent and actionable for users. We argue that this gap between generating valid CFXs and communicating model behavior stems from the lack of user-centered abstraction and limited qualitative evaluation. To bridge this gap, we investigate large language models as mediators that summarize raw CFX interaction edit lists into concise natural language explanations describing higher-level preference patterns. We optimize these mediators for correctness, informativeness, and linguistic quality through preference optimization, and evaluate the resulting explanations with human-calibrated metrics derived from separate human-labeled datasets. On the MovieLens-1M dataset, across multiple counterfactual generators and language models, the resulting summaries achieve high overall linguistic quality, while the strongest semantic results are obtained with high-success CFX methods such as ACCENT and SPINRec. Direct Preference Optimization improves the semantic metrics in almost all evaluated settings.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13914
PDF
-
Minimax Rates and Spectral Distillation for Tree Ensembles
Abstract
Tree ensembles such as random forests (RFs) and gradient boosting machines (GBMs) are among the most widely used supervised learners, yet their theoretical properties remain incompletely understood. We adopt a spectral perspective on these algorithms, with two main contributions. First, we derive minimax-optimal convergence for RF regression, showing that, under mild regularity conditions on tree growth, the eigenvalue decay of the induced kernel operator governs the statistical rate. Second, we exploit this spectral viewpoint to develop compression schemes for tree ensembles. For RFs, leading eigenfunctions of the kernel operator capture the dominant predictive directions; for GBMs, leading singular vectors of the smoother matrix play an analogous role. Learning nonlinear maps for these spectral representations yields distilled models that are orders of magnitude smaller than the originals while maintaining competitive predictive performance. Our methods compare favorably to state of the art algorithms for forest pruning and rule extraction, with applications to resource constrained computing.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11841
PDF
-
Persistent Metric-Semantic Maritime Scene Memory from Open-Vocabulary 3D Scene Graphs
2026-11-10 10:59:07Kim Alexander Christensen, Dina Zimmermann, Martin Steinert, Eleni KelasidiAbstract
Three-dimensional scene graphs (3DSGs) can provide robots with persistent metric-semantic representations for spatial reasoning, but the existing methods have primarily been developed for indoor and terrestrial environments. In this paper we investigate how a representative outdoor open-vocabulary method transfers to maritime environments and which adaptations are needed. Our experiments show that zero-shot representative outdoor 3DSG descriptions agree with our labeled ground truth for a majority of geometry-supported objects on our data, but the resulting map exhibits considerable physical-entity fragmentation, and its terrestrial higher-level assumptions don't capture maritime spatial organization needs. We therefore keep the underlying mapping method and post-process its accumulated evidence. We show a metric-semantic consolidation method followed by geometry-grounded multi-view vision-language model (VLM) reasoning that reconciles remaining fragments into physical entities and groups entities through observations into local places. In parallel, we construct maritime macro regions using map priors and onboard water and structure observations, and associate them with the local places. The resulting representation reduces physical-entity fragmentation beyond both the baseline and our geometry-semantic consolidation component alone, supports correspondence of fixed local places across repeated maritime traversals, and improves contextual retrieval on our reviewed queries over tested baselines. These results show how an outdoor open-vocabulary map can be adapted into persistent maritime scene memory with our methods for object/place identity and spatial abstractions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13903
PDF
-
Beyond Fluent Responses: Finding User Dissatisfaction in Human-AI Interactions
2026-11-10 10:54:11Yuka Saito, Ikumi Numaya, Jun Suzuki, Reina AkamaAbstract
As large language models generate increasingly high-quality responses, recent work on response evaluation has moved beyond response-centered criteria, such as correctness and coherence, toward user-centered criteria, including user preferences and perceived usefulness. This shift is fundamentally important for developing technologies that are truly useful to real-world users. While conventional response evaluation quantifies the quality of the response itself, users' satisfaction in real conversations also depends on their subjective preferences and perceptions of usefulness, which do not necessarily align with response quality. This study investigates whether such user-centered signals can be detected from conversational text. Specifically, we analyze user utterances with self-reported dissatisfaction labels to examine whether user dissatisfaction in text can be detected. In English interaction, models using user utterances exceeded the 17.8% dissatisfaction label prevalence in AUPRC by up to 15 percentage points. These results suggest that user utterances reveal cues to implicit dissatisfaction. Furthermore, changes from the immediately preceding user utterance may improve dissatisfaction detection, with anomaly detection methods appearing particularly effective.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13894
PDF
-
Polarization Aware Deep Learning Framework for SAR Despeckling
2026-11-10 10:25:36Gianpaolo Passarello, Sergio Vitale, Hossein Aghababei, Giampaolo Ferraioli, Vito PascazioAbstract
Speckle is an inherent characteristic of synthetic aperture radar (SAR) imagery that complicates image interpretation and the extraction of reliable information. Although deep-learning-based despeckling methods have demonstrated promising performance, their applicability across different polarimetric configurations is often limited by the need for specialized architectures or separate training procedures. This paper presents a unified deep-learning framework for despeckling single-, dual-, and full-polarization SAR data using a single trained convolutional neural network. The proposed approach adopts a common nine-channel representation of the polarimetric covariance matrix and a polarization-aware masking strategy to accommodate different configurations without modifying the network architecture. Qualitative and quantitative comparison on three different scenes from different sensors demonstrate competitive performance across the considered experiments and support the feasibility of a unified, polarization-flexible approach to SAR despeckling across different polarimetric configurations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10091
PDF
-
Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics
2026-11-10 10:11:30Bastien Dussard (LAAS-RIS, LAAS), Aur{\'e}lie Clodic (LAAS-IDEA, LAAS-RIS, LAAS), Guillaume Sarthou (LAAS-RIS, EPE UT, LAAS)Abstract
While symbolic reasoning for task allocation requires grounding a robot's physical capabilities, standard Unified Robot Description Format (URDF) files provide only low-level kinematics without the formal semantic context needed for reasoning. We present URDF2Ontology, an automated, taxonomy-agnostic neurosymbolic framework that transforms raw URDF files into populated, grounded OWL ontologies. It leverages a Large Language Model (LLM) for targeted semantic reasoning, coupled with an iterative sequential graph-purging mechanism to prevent context window saturation. To process complex kinematic structures, it employs a morphology-aware dual-track architecture featuring a bottom-up Tree Track for branching assemblies and a top-down Chain Track for serial limbs. Guided by neurosymbolic guardrails, the framework extracts functional sub-graphs and asserts populated ontologies aligned with arbitrary user-provided taxonomies. Empirical evaluation across a diverse fleet of heterogeneous robots demonstrates strong schema alignment, valid structural extraction, and a significant reduction in manual domain authoring overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13850
PDF
-
Oscillatory Processing Units as a computing substrate for biomimetic intelligence
Abstract
Biological intelligence emerges from neural activity that connects sensation, memory and action. Synaptic plasticity, neuronal assemblies and oscillations provide principles for biomimetic computing, but translating them into reusable operations requires a defined computational unit. We introduce Oscillatory Processing Units (OPUs), groups of synthetic neurons sharing a rhythm. Their directed interactions transform incoming activity and prior receiving state into an Oscillatory Occupancy Space (OOS), which becomes available to subsequent computation. We show that source--receiver conditions and oscillatory organization shape these transformations, including their geometry, persistence and historical accessibility. An Atlas of measured relationships supports prospective composition with predicted response classes. Configured circuits perform logical and numerical operations, express associative recall and generate closed-loop decisions with fixed synaptic weights. OPUs and OOS establish a computing substrate for biomimetic intelligence in which experience remains part of the state through which new input becomes action.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13840
PDF
-
Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation
2026-11-10 09:57:01Luca Favole, Giorgio Mongardi, Giovanni Squillero, Alberto TondaAbstract
The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to assess the capability of Artificial Intelligence (AI) systems to generalize starting from a few samples, a task humans excel at. The ARC-AGI contests held since 2020 have been the focus of intense competition, with participants proposing approaches ranging from traditional symbolic AI to Transformer architectures. Despite a long history of successes, evolutionary algorithms (EAs) were notably absent from the approaches appearing in the main contest. As score-and-search program synthesis approaches, EAs suffer from issues related to choosing the proper representation in the Domain-Specific Language applied to the problem (for example, pixel-level or object-level), and distinguishing between two candidate solutions producing the same outputs. In this work, we present the first fully symbolic, evolutionary-based program synthesis approach submitted to the ARC-AGI-2 main contest. The main contributions are: evolving the grid parser and the output projector together with the program that transforms the grid, so that a task-specific language emerges during program synthesis; grounding the symbols the parser can extract in core knowledge theory from cognitive psychology; and an object-aware fitness that grades partially correct outputs beyond pixel-level discrepancies.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13831
PDF
-
Game-Enhanced Embodied Learning with Event and Foresight Pretraining
2026-11-10 09:46:21Lianlei Shan, Han Jin, Yaunchao Ma, Xinpeng Chen, Linhao Zhou, Xin BinAbstract
Human gameplay supplies paired observations, actions, and visual consequences that can supplement robot-policy training. We study event-and-foresight pretraining for InternVLA-A1.5, combining recorded keyboard/mouse event prediction with history-conditioned visual supervision through a frozen video model. Coverage-preserving anchor selection constructs one-second targets, and an attention mask prevents teacher-forced future actions from entering foresight queries. The selected corpus contains 394 recordings across 20 games, with 223.36 hours of recorded timestamp span and 2,072,084 training anchors. After 12,400 game-pretraining updates, we compare the resulting initialization with the public base under the same suite-specific robot fine-tuning protocol. Across four LIBERO suites, aggregate success increases from 1,718/2,000 (85.90%) to 1,811/2,000 (90.55%), a gain of 4.65 percentage points. Suite gains are 9.2, 6.8, 0.2, and 2.4 points on Spatial, Object, Goal, and Long. The 40-task breakdown shows 24 improvements, 10 declines, and six ties. These results support the practical value of the complete game-pretraining stage in this evaluated setting, while revealing heterogeneous task outcomes. The comparison includes additional optimization and does not isolate the effects of game data, the two objectives, or training variability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13819
PDF
-
WAM is capable in BEHAVIOR-1K: the 2nd-place solution to the 2026 BEHAVIOR Challenge
2026-11-10 09:46:02Yelin He, Jiaquan Ye, Xinming Wei, Wenjie Xiao, Gengming Zhang, Guoting Wei, Xianbiao Qi, Rong XiaoAbstract
This work presents the 2nd-place solution (Team IF1001) to the 2026 BEHAVIOR Challenge, which evaluates mobile manipulation across 100 household tasks. Our method is built on a powerful world action model (WAM), Cosmos 3. We improve Cosmos 3 by using richer visual history, task-progress conditioning, and task-group and skill-specific LoRA adapters. During inference, we apply a separate progress estimator to supply task-progress context, and use task- and progress-conditioned routing to select a task-group or skill-specific policy, complemented by action-candidate aggregation, rolling inpainting, and task-specific temporal and gripper control. To meet the minimum inference requirement of 1 FPS, we use neither recursive self-improvement (RSI) nor agentic harness methods and rely on no closed-source models; during official private-test evaluation, our system handled concurrent requests across 100 evaluation ports with limited hardware resources, sustaining an average end-to-end inference rate above 2 FPS per port. Our method achieves a mean Q-score of 0.613 and a full-task success rate of 40.9%, averaged over 3 self-evaluation rounds across all 100 tasks. On the official private test set, with 20 instances per task, our system achieves a mean Q-score of 0.615 and a full-task success rate of 41.2%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13818
PDF
-
Camera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm
Abstract
Real-robot benchmarks of learned visuomotor policies often record room illuminance as the lighting condition. We show that, on a typical low-cost rig, room light and image light can be almost unrelated. Four imitation-learning policies (ACT, SmolVLA, Diffusion Policy and pi0.5) were trained on the same 50 demonstrations of a pick-and-place task on an SO-101 arm. Each was run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera. Both cameras were set to automatic exposure and white balance, which most likely absorbed the difference; exposure was not locked in this experiment. An accidental repeat of one 10-rollout block reproduced its success count (7/10) but matched the first block at only 6 of 10 placements, consistent with chance. We conclude that lux alone does not describe what a policy sees. Camera settings, and image statistics compared with the training recordings, are the quantities to report and control. Data and code are public.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13810
PDF
-
Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data
2026-11-10 09:34:28Hang Li, Jiaxin Qi, Yan Cui, Yuhua Zheng, Jianqiang HuangAbstract
Motivation: Gene regulatory networks (GRNs) capture the underlying interactions through which transcription factors (TFs) regulate genes. Based on gene expression data, existing GRN inference approaches generally fall into two categories: graph-based methods, which model the GRN as a whole graph, and pairwise-based methods, which decompose the GRN into individual TF-target gene pairs for modeling. However, each approach exhibits limitations that are precisely the strengths of its counterpart. Graph-based methods tend to overfit due to their reliance on a single training graph, whereas pairwise-based methods benefit from abundant TF-target training pairs. In contrast, pairwise-based methods overlook the global topological structure, which is essential for comprehensively capturing regulatory mechanisms. Results: To address these limitations, we propose scGPL, an end-to-end unified framework that jointly models global regulatory topology and local interactions. scGPL extracts macro-level features from the global regulatory graph and introduces a dynamic, importance-guided subgraph sampling mechanism to capture fine-grained local dependencies. By fusing global representations with subgraph-enhanced local features, our framework bridges the gap between the two paradigms, incorporating essential whole-graph topological dependencies while retaining the data abundance advantage of pairwise methods. Extensive experiments on seven benchmark datasets demonstrate that scGPL consistently achieves state-of-the-art performance, with up to 13.7% improvement over the strongest baseline, validating the effectiveness of our integrative design. Availability and implementation: The source code is maintained on GitHub (this https URL), and the datasets and versioned releases are archived at this https URL for reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13801
PDF
-
How Many Demonstrations Does a VLA Need? On the Sample Efficiency of VLA Finetuning
Abstract
Pretrained vision language action (VLA) models show strong zero-shot performance but they are rarely deployed directly and are often first post-trained on demonstrations from the target setting. Yet VLAs are typically compared by zero-shot or full-data fine-tuned success which reveals little about the data and compute required for downstream adaptation. We study adaptation efficiency for six VLAs ($\pi_0$, $\pi_{0.5}$, and GR00T N1-N1.7) on four LIBERO suites, varying both demonstrations and training steps. This reveals differences hidden by full-data fine-tuning: models which are within two points on the full LIBERO-Spatial dataset differ by up to 3$\times$ in success with 50 demonstrations. $\pi_{0.5}$ needs 2-5$\times$ fewer demonstrations than $\pi_0$ and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite. Within GR00T, N1.5 adapts more efficiently than N1.6 and N1.7 on three of four suites, despite their stronger zero-shot performance. We also study one pretraining factor behind these differences by freezing the VLM during finetuning: this severely degrades the $\pi$ models whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09964
PDF
-
Integrating Action Prefix Prediction and Alignment Across Modalities for Multimodal Reinforcement Learning
2026-11-10 09:20:04Sijie Xu, Francisco CruzAbstract
Learning representations from multimodal observations is difficult in reinforcement learning with limited interaction data. Multimodal Joint Predictive Representation combines multimodal latent prediction with contrastive learning across modalities, but its recursive rollout depends on earlier predictions and its pairwise alignment focuses on correspondence between modalities. We propose Improved Predictive Representation, which combines prediction from action prefixes with alignment at the observed anchor based on Contrastive Multimodal learning. At each horizon, it predicts future representations directly from the observed anchor and the corresponding sequence of actions. We evaluate two crop configurations: IPR-S with a minimum retained crop area of 10%, and IPR-H with 50%. Across five DeepMind Control Suite tasks, IPR-H achieves an average return across tasks that is 10.0% higher than the baseline with visual and depth images and 3.4% higher with visual images and position vectors. The relative performance of the two configurations varies across tasks. In Webots, both IPR configurations achieve higher mean final returns than the baseline without LiDAR, but not when LiDAR is available.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13782
PDF
-
OASIS: Optimization-Aware Subgoal Inference with Safety Constraints for Autonomous Mobile Robot Navigation
2026-11-10 09:14:15Arian Hajizadeh, Javad Pourrafi Arabani, Negar Shenavar, Sana Bashiri, Seyed Majid EsmailzadehAbstract
Navigation in dynamic environments requires mobile robots to make progress toward their goals while respecting motion limits and avoiding surrounding obstacles. Learned subgoal policies can guide model predictive control beyond its local prediction horizon, but a geometrically suitable subgoal does not necessarily lead to a successfully solved control problem. This paper proposes OASIS, a hierarchical navigation framework that incorporates recent optimization outcomes into reinforcement learning-based subgoal generation. A high-level policy trained using Soft Actor--Critic generates local subgoals, while a nonlinear model predictive controller tracks them subject to motion limits, geometric collision-avoidance constraints, and embedded high-order control barrier function constraints. The outcomes of controller optimizations over each subgoal interval are summarized and provided to the policy at its next decision, without requiring additional optimization calls. The framework is evaluated in five navigation scenarios with static and moving obstacles, including dense interactions and sensing uncertainty. Comparisons with hierarchical and direct-goal control variants show that OASIS achieves the highest aggregate navigation success. Matched comparisons across three training seeds further show a consistent success advantage over the otherwise identical hierarchy without optimization-status input. The selected-policy comparison also shows fewer primary optimization failures with similar mean controller time.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11996
PDF
-
MSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information
2026-11-10 09:06:09Xinyu Chen, Liangjian Wen, Jiang Duan, Dongkai Wang, Yong Dai, Jiayu Bai, Jianzhuang Liu, Zhen Tian, Guoping Qiu, Zhao KanAbstract
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-oriented methods such as the Multimodal Competition Regularizer (MCR) perform well by alleviating this imbalance during training. These dynamic balancing methods, however, mainly adjust modality contributions and do not consider how imbalance affects the formation of synergistic information during fusion. Synergy is a major source of multimodal advantage, because it is predictive gain that cannot be recovered from unimodal evidence alone. We propose the Multimodal Synergistic Competition Regularizer (MSCR), a fusion method that jointly promotes balanced modality utilization and the discovery of synergistic information. MSCR has two complementary objectives. An anti-dominance objective suppresses excessive unimodal influence and leaves room for synergistic information, and a synergy objective encourages the fused predictor to outperform a non-synergistic unimodal reference. An adaptive gate further concentrates the regularization on samples that need stronger collaborative modeling. Experiments on five benchmarks show that MSCR consistently improves performance over MCR and strengthens synergistic capability. It raises conditional recovery, the accuracy of the fused prediction on samples that the unimodal predictors misclassify, as well as the share of the model's output that InterSHAP attributes to cross-modal interactions. Its gain in conditional recovery persists when the fusion module is Transformer-based. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.24395
PDF
