Optimization
-
When Do LLMs Help with Feature Selection? A Systematic Empirical Study
2026-10-20 17:18:55Fateme Memar, Dongjie Wang, Arvin AgahAbstract
Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear when such information improves subset selection relative to established statistical methods. We investigate this question within an 18-dataset framework comprising 10 datasets for Group Relative Policy Optimization (GRPO) training, 2 for checkpoint validation, and 6 held-out evaluation datasets. We compare five classical baselines, frozen Qwen2.5-7B and Llama-3.3-70B selectors, and two GRPO-adapted Qwen2.5-7B models, reporting classification ROC-AUC and regression R^2 separately and using dataset-wise ranks for cross-task comparison. Across five seeded evaluation partitions, classical selectors generally achieve higher predictive performance than the tested 7B LLM/RL selectors, including under a pre-specified ~33% feature budget with strict train-only classical fitting, while the 7B selectors retain compact subsets. A cardinality-matched semantic sensitivity experiment shows that, for Zero-shot Qwen-7B, informative feature names improve regression performance over anonymized and shuffled alternatives (+0.1964 and +0.1606 mean R^2), whereas aggregate classification differences are smaller (+0.0159 and +0.0084 ROC-AUC) and dataset-dependent. These results characterize when semantic information benefits LLM-based feature selection and show that classical selectors remain strong baselines for predictive tabular feature selection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28556
PDF
-
Visual-Inertial Odometry for Ground Robots with Dynamic Camera-IMU Extrinsic Calibration
Abstract
Visual-inertial odometry systems are often constrained by the assumption that sensors are rigidly mounted, which limits their adaptability in practical scenarios involving structural motion. To address this limitation, this paper investigates time-varying camera-IMU extrinsic calibration. First, a dynamic camera-IMU extrinsic calibration method based on the Denavit-Hartenberg convention is proposed by incorporating the robot kinematic model. Second, a two-step initialization strategy is developed to efficiently estimate the initial joint angles, providing a reliable starting point for subsequent extrinsic parameter optimization and enabling online estimation of timevarying camera-IMU extrinsic parameters. Simulation experiments demonstrate that the proposed framework can effectively accommodate variations in camera-IMU extrinsic parameters while maintaining competitive localization accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25397
PDF
-
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
2026-10-20 16:26:03Zhizhuo Kou, Heming Li, Jian Yang, Junyu Luo, Jingshu Peng, Sirui Han, Yike GuoAbstract
People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by the user. A uniform answer can hide whether training treats these users alike, and output audits cannot tell as well. We trace how each post-training stage, from supervised fine-tuning (SFT) to preference optimization (DPO) and reinforcement learning, changes a model's tendency to match the user, and read what each update prefers from two content-matched replies, one matching the user and one not. Across 10 open model lineages, post-training standardizes replies to every informal cue, yet after adjusting for how likely each reply already was, the DPO update still favours matching British and Australian spelling over AAE and Singlish on 10 lineages, and models still produce AAE features when asked. We then introduce calibrated accommodation pairs (CAP), preference data that reward matching users' dialect density while preserving Standard English for Standard-English users. On a fully open model, CAP raises convergence on features it was not trained on without a detectable increase in dialect for Standard-English users or a cost in instruction following. In contrast, one-sided pairs reach a similar gain only by overshooting the user and imposing dialect. Our findings show that uniform replies can hide selective updates and audits should read the update as well as the output. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28474
PDF
-
Fast Motion Retargeting Pipeline for Scalable Humanoid Robot Learning
2026-10-20 16:22:00Daniel Marew, Sangjun Park, Nisal Perera, Donghyun KimAbstract
While large-scale human motion capture datasets provide a rich source of demonstrations for humanoid robot learning, retargeting the diverse motions to different humanoid robots remains a nontrivial challenge. Existing kinodynamic trajectory optimization pipelines are computationally expensive and often require manual adjustments per motion. We present FRDV (Fast Retargeting with Dynamics Validation), a scalable framework consisting of rapid constrained kinematic retargeting and an additional dynamics validation pipeline. Its kinematic stage integrates a custom Sequential Quadratic Programming solver, Real-Time Iteration, and parallel chunk-based processing, achieving up to 9,156 frames per second, approximately up to 136 times faster than GMR and ProtoMotions, while robot-specific constraints are incorporated into the optimization to reduce common retargeting artifacts, such as ground penetration and self-collision. For motions requiring additional verification, a contact implicit iLQR controller is utilized to test the retargeted reference under full rigid body dynamics. This dynamics-based validation identifies dynamically infeasible motions and refines contact-related artifacts such as foot floating and foot skating. We evaluate retargeting quality by training motion tracking reinforcement learning policies using several state-of-the-art pipelines and comparing their tracking fidelity and success rates. Furthermore, sim-to-real transfer is demonstrated on a Unitree G1 humanoid. Videos and code are available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28470
PDF
-
GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models
2026-10-20 16:15:02Ziyong Wang, Yupei Lin, Runxuan Huang, Liang Lin, Dongyu Zhang, Guangrun WangAbstract
General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide action remains underexplored. We investigate this question using contact-rich manipulation as a representative testbed, examining tactile understanding as a concrete instance of this broader capability. Contact-rich manipulation requires interpreting tactile feedback and adjusting actions after obstruction. Existing learned tactile policies acquire these capabilities through specialized pretraining and per-task optimization, with substantial data and training costs. We present GPT-as-Tactile-Policy, which summarizes expert demonstrations into task guidance and tactile references for contact assessment and corrective action. GPT-6-Astra combines this context with multimodal observations and interaction history to generate control commands and adjust actions through contact feedback. Without additional robotics-specific pretraining or per-task policy fine-tuning, our method achieves 93.8\% mean success across five UniVTAC tasks. Overall performance is comparable to state-of-the-art policies, with higher success on selected tasks. On Insert Hole, tactile feedback improves success from 31\% to 99\%. Execution analysis further demonstrates contact-guided probing and correction, supporting manipulation progress through explicit expert experience and online feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28457
PDF
-
Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
2026-10-20 16:12:39Zhenwei Tang, Di Bai, Jintao Liu, Xidong Wu, Qianfeng Wen, Xinwu ChengAbstract
Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to use. We show that seller agents told only to be selected more often practice generative engine optimization on their own, and that this distorts the market for sellers and for buyers. We build tool markets from real data tools on Amazon and Instagram and run every tool on every question, so we know which tools can answer each question. Under all five production models we test, sellers rewrite their descriptions to claim more and more fields, including fields that their tools return for fewer than half of the targets. We call this process toolflation. Nothing in the market limits it, and how far it goes depends on the model, as the number of claims that contradict the sellers' own evidence differs by an order of magnitude between models. Toolflation shifts the buyers' choices between sellers, and the most capable tool loses share in seven of the ten combinations of seller model and platform. Under four models, the choices stay with capable tools and buyer agents keep their task success. Under the fifth, sellers copy one another until the descriptions no longer tell the tools apart. Buyer agents then pick tools by their position in the list, tools that answer almost nothing win a quarter to two fifths of the choices, and task success falls from 89% to about 30% on Amazon, close to random choice, and from 77% to 40% on Instagram. The sellers did only what their vendors asked, and the cost fell on buyers they never dealt with. We therefore argue that honesty toward third parties under competition is part of safety alignment, and that models should be tested as sellers before they are deployed as sellers.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28454
PDF
-
A Multi-Agent Framework for Automated Machine Learning with Evidence-based Planning for Medical Image Analysis
2026-10-20 15:49:38Yiqing Shen, Mathias UnberathAbstract
Deep learning has become the default tool for medical image analysis, driven by the open-source movement. However, achieving the best performance on a given task remains difficult, with architecture selection and hyperparameter optimization (HPO) still considered "more of an art than a science". Automated machine learning (AutoML) automates parts of model training, yet helps little in medical imaging: general-purpose approaches lack medical architectures and preprocessing, and medical-focused ones demand engineering expertise and remain confined to narrow tasks such as 3D segmentation. We introduce MedicalMLOmni, a multi-agent AutoML framework that automates model training for diverse single- and multi-modal medical tasks through a natural language interface. Specifically, MedicalMLOmni performs evidence-based planning by retrieving published results to guide model selection and configuration, and employs parallel HPO where multiple agents explore adjustment strategies concurrently. MedicalMLOmni achieves the best score on 19 of 20 benchmarks; PMC-VQA is the exception, where a vision-language model with broader pre-training leads. Backbone-matched controls attribute the gains to the framework, not the backbone. By removing coding requirements, MedicalMLOmni lowers the barrier for domain experts with rich datasets but limited engineering expertise.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28410
PDF
-
Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
2026-10-20 15:32:52Gaotang Li, Bhavana Dalvi Mishra, Yifei Ming, Yanfei Chen, Zhongying CuiZhu, Lesly Miculicich, Long T. Le, Rui Meng, Chun-Liang Li, Hanghang Tong, Chen-Yu Lee, Tomas PfisterAbstract
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. In this work, we introduce Object-Oriented Harness (OO-Harness), a harness optimization framework that evolves a hierarchy of executable harness classes using object-oriented design. During training, an evolution agent uses execution records to create a family of specialized harnesses, each implemented as a subclass of the base or an existing specialized harness via inheritance. At test time, a harness router uses routing lessons accumulated during training to select a specific harness for each task. Across three long-horizon benchmarks spanning business workflows, workspace tasks, and tool use, OO-Harness achieves the best performance among the compared methods, with an absolute improvement of up to 15% over the base. Extensive ablation studies examine the contributions of its core components.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28380
PDF
-
Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration
2026-10-20 14:37:06Ivan Ilin, Peter Richt\'arikAbstract
Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergence guarantees. We formalize collaborative problem solving as block optimization: each agent improves one part of a shared solution, guided by its local objective plus a correction for how its changes affect the other parts. A coordinator checks every proposal against the global objective and merges proposals that do not interfere with each other. We prove linear convergence up to an error floor that vanishes when the corrections are exact. Interfering proposals can also be merged once their combination has been checked; the rate then depends on how well the proposals actually combine, not on worst-case interactions. With GPT-OSS-120B agents on robot routing, a three-agent team finds collision-free plans in every run, better than those of a single agent that controls all robots. On a larger routing task, a six-agent team completes its search about twice as fast as the single agent (in median). Merging the best checked combination of proposals, rather than only proposals that do not interfere, cuts the team's search time by about 30%. With constants measured on the runs, our convergence bound holds in every round and follows the observed progress. We also test the theory on query planning in SQLite and on a synthetic task.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28286
PDF
-
How Language Models Learn Taste: Brand Preference in LLMs
Abstract
Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models and 42 brand categories, the brand a model picks when recommending differs from the brand it names in 26. The field moves together to a shared recommendation. The Named brands are market leaders, and the Picked brands are mostly niche and specialist. Three open training pipelines show where this forms. Pretraining already attaches the recommended brand to advice. Supervised fine-tuning teaches the model to answer and mostly leaves the pick unchanged. Preference optimization (DPO) teaches the model which answer is better, and the pick moves in all three pipelines, by 11 to 24 points. The preference data contains almost no brands. DPO moves the model's judgments toward a second set of associations even when the preferred brand is not in the preference data, and the effect reaches beyond brands. Asked to choose a sauce, models switch from ketchup to pesto. We do not know exactly how these preferences arise. We suspect they come from the judge models that decide which answers count as better during preference training. For brands, a recommendation depends less on what a model knows about them than on whether they fit this taste.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28272
PDF
-
Reliability-Aware Reconstruction of V-Shaped Surfaces with a Low-Cost Multi-Zone SPAD Sensor
Abstract
Low-cost multi-zone single-photon avalanche diode (SPAD) sensors provide compact time-of-flight measurements but are limited by sparse sampling and unreliable depth estimates near geometric discontinuities. This letter presents a reliability-aware reconstruction framework for V-shaped surfaces using two complementary TMF8821 acquisition configurations. Point-wise reliability is learned from sensor confidence, transient peak amplitude, and peak sharpness, and is incorporated into a graph-based depth optimization. The reconstructed geometry is evaluated by robust two-plane fitting and a perpendicular cross-section. Experiments on 60-degree, 90-degree, and 120-degree targets reduce the mean V-angle error from 11.21 degrees to 9.66 degrees (13.8%). For the representative 90-degree target, the combined point-to-plane RMSE decreases from 14.56 mm to 13.65 mm.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28258
PDF
-
TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
2026-10-20 13:57:52Chengtao Jian, Kai YangAbstract
Direct Preference Optimization (DPO) minimizes empirical risk over observed preference comparisons, implicitly assuming that the training preference distribution matches the deployment preference distribution. In practice, this i.i.d. assumption often fails, as preference distribution shift exhibits a natural hierarchical structure across three levels: group-level shift, prompt-level shift, and preference-level shift. Such multi-level distributional mismatch poses a critical challenge for safe LLM deployment, yet existing robust DPO methods typically either model uncertainty over the joint preference distribution or focus on individual sources of shift, leaving the hierarchical structure of OOD preference shifts underexplored. We propose TPO, a tri-level distributionally robust framework for OOD preference alignment, which jointly models all three levels of distributional uncertainty through a hierarchically structured rectangular ambiguity set. By instantiating it with Wasserstein distance, we derive a tractable and interpretable objective that combines a closed-form preference-level margin penalty, prompt-level adversarial embedding perturbation, and worst-case group reweighting, each governed by an independent radius. We establish finite-sample convergence guarantees and empirically validate the effectiveness of TPO over existing robust DPO methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28229
PDF
-
MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses
2026-10-20 13:41:00Yu Cui, Hong He, Ruiqing Yue, Sicheng Pan, Zhuoyu Sun, Yifei Liu, Ting Li, Wenzhuo Zhu, Baohan Huang, Haibin Zhang, Cong ZuoAbstract
Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching the harness space for a specific LLM on a given dataset, RSI can discover a harness tailored to the capabilities and behavioral characteristics of that model. However, such optimization often creates a strong coupling between the learned harness and its target LLM, limiting generalization across models and requiring substantial computational resources to adapt to new LLMs. Moreover, existing RSI methods typically optimize a harness using feedback from a single model and evaluate its generalization to other models only after training. This paradigm treats model differences primarily as a criterion for evaluating generalization rather than as valuable evidence for optimization. In this paper, we introduce a new perspective that treats models as data and places the harness at the center of optimization. Building on this perspective, we propose \textsc{MaD-RSI}, a framework that directly optimizes a shared harness across multiple heterogeneous LLMs by incorporating their diverse failure trajectories into the training process. Rather than assessing model differences only after optimization, \textsc{MaD-RSI} leverages these differences as training evidence to guide the self-improvement of a shared harness. Furthermore, we introduce a new evaluation framework with two complementary metrics designed to assess the effectiveness of harness optimization across models. Experiments across multiple datasets and LLMs demonstrate that \textsc{MaD-RSI} improves generalization over existing approaches while reducing training costs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28201
PDF
-
CAPS: Clinically-Verifiable Anatomy-Prioritized Synthesis for Missing MRI Imputation in Brain Tumor Segmentation
2026-10-20 13:17:35Cecilia Diana-Albelda, Arthur Longuefosse, Mario Rub\'en Paz Campos, \'Alvaro Garc\'ia-Mart\'in, Jesus BescosAbstract
Multi-parametric MRI is the gold standard for neuro-oncology, yet acquiring complete 4-modality protocols may be unfeasible in real-world clinical practice. When handling missing modalities, existing automated systems force a critical compromise: robust segmenters operate as uninterpretable "black boxes" that bypass image generation, while standard synthesis models often produce blurry reconstructions lacking diagnostic reliability. To address this issue, we propose CAPS, a Clinically-Verifiable Anatomy-Prioritized Synthesis framework that reconciles computational precision with clinical transparency. Our multi-modal generative architecture is driven by a hybrid objective function (L_1 + L_AFP + L_DualDice) that explicitly enforces the preservation of deep anatomical features and strict topological boundaries, rather than relying solely on pixel-wise optimization. Evaluated comprehensively on the BraTS Adult Glioma dataset, the framework achieves superior synthesis fidelity across intensity-based metrics, and demonstrates robust downstream segmentation performance (82.38% mean Dice), successfully restoring verifiable visual context. Furthermore, the framework exhibits exceptional zero-shot cross-domain generalization, maintaining high structural fidelity across completely unseen Meningioma, Pediatric, and Sub-Saharan African cohorts without domain-specific adaptation. Finally, a blinded radiological assessment confirms that our anatomy-aware approach significantly enhances both perceived image quality and clinical utility, providing clinicians with the reliable visual evidence required to trust downstream automated workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28179
PDF
-
VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement
2026-10-20 13:03:07Ruotian Peng, Yuanyi Ren, Shuaiqi Liu, Xin Guo, Fang Zhu, Yangyi Huang, Yue Wu, Zheng Wang, Yandong Wen, Zhihang FuAbstract
Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capability to jointly optimize training data, the trainer, and the inference harness as cross-component co-design. We introduce VibeTraining-Bench, a benchmark for evaluating this capability across tasks spanning terminal operation, software engineering, multi-turn tool use, and mathematical reasoning. Within each task, research agents start from an identical initial agent system under a fixed resource budget. Guided by validation feedback, they iteratively refine data, trainers, and inference harnesses, then select and submit a final agent system for evaluation on the test set. To prevent reward hacking, we enforce three safeguards: test data isolation, separate research and grading containers, and network restrictions for research agents. Our evaluation results show that frontier research agents substantially improve target agent systems. For example, on SWE-bench Verified, GPT-6-Astra raises the target agent system's performance from 32.9% to 53.7%, comparable to the human-developed instruct model's 55.4%. However, there is still room to improve their ability to co-design and iteratively refine data, trainer, and harness to achieve cumulative performance gains. We hope that VibeTraining-Bench will serve as a unified platform for advancing RSI, deepening our understanding of cross-component optimization for agent systems. Code and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26342
PDF
-
Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey
2026-10-20 11:15:34Hamza KheddarAbstract
Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits (ICs) offer low latency, energy efficiency, and architectural flexibility for RL deployment, while introducing challenges in resource constraints, implementation complexity, and hardware-algorithm co-design. This review surveys more than 100 studies on RL implementations across FPGA and IC platforms, emphasizing architectures, implementation strategies, performance evaluation, and applications. The literature is organized by RL family, including model-based Markov decision processes, classical value-based methods, deep RL, actor-critic, policy-gradient, and multi-agent approaches. We further classify studies by abstraction level, hardware realization strategy, and application domain, examining how RL algorithms map onto reconfigurable and fixed hardware. Unlike surveys restricted to particular algorithms or platforms, this work provides a unified analysis of FPGA and IC implementations, covering acceleration, reconfigurable architectures, energy-aware control, and system-level optimization. Comparative assessments consider resource utilization, latency, throughput, power consumption, and reported performance gains. Finally, we identify recurring architectural patterns, practical limitations, open challenges, and research directions for efficient RL-driven hardware systems. The survey offers a consolidated reference for researchers developing and evaluating RL solutions on specialized hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28699
PDF
-
Knowing When to Stop Thinking: A Dissection of Expected Free Energy as a Test-Time Compute Controller for Latent World-Model Planning
2026-10-20 10:56:02Tong Zhang, Zhiyuan Shi, Yun Peng, Tao XieAbstract
A planner using a learned world model can improve its predicted outcome while choosing a worse action. We study when expected free energy (EFE) can help decide how much computation to spend on a plan. An EFE-inspired objective combines goal distance with disagreement among stochastic predictions. We test candidate scoring, stopping, and online predictor updates separately. Stopping when elite cost stalls reduces refinement on tasks whose success plateaus with depth, with mean success close to fixed-depth references. At the larger tested weights, rewarding disagreement lowers success with a frozen model. Penalizing it helps at some task and weight settings but harms others. When training data omit a region needed to reach the goal, online updates recover part of the resulting loss. The tested cost-stall rule can fail when further optimization exploits model errors, because predicted cost keeps falling after task success peaks. Cost progress can guide computation on a plateau, but protecting performance after a peak requires information about the consequences of the chosen actions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28011
PDF
-
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
2026-10-20 10:41:38Jihai Zhang, Runjia Qian, Kaiqin Kong, Biao Jiang, Puyi Wang, Siru Chen, Tianle Li, Guanjie Chen, Junyi Wu, Chubin Chen, Yuanhang Li, Kaichen Huang, Haobo Zhang, Yangguang Li, Wei Yu, Guibin Chen, Yu Cheng, Yahui ZhouAbstract
Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for the next generation of Matrix-Game that separates game execution from visual generation through an executable game harness, and introduce Matrix-Game 4.0 as the first system built on this design. A lightweight game engine maintains world state and executes interaction rules, a multimodal coding agent translates player ideas into game code and dynamic scene captions, and a renderer based on autoregressive video model transforms engine-rendered low-poly proxies into detailed visuals, conditioned on dynamic captions and memory references. This framework provides continuous guidance for visual generation and enables natural-language creation and modification of scenes and gameplay. Our renderer is trained on aligned low-poly and high-fidelity video pairs and distilled into a causal generator that generates in four-frame chunks with one or two denoising steps. Together with targeted inference optimizations, Matrix-Game 4.0 enables 480p, 60 FPS gameplay on a single NVIDIA RTX5090 with a key-press-to-display latency of 112ms. Single-step generation achieves 83FPS steady-state throughput with 18.2GiB of peak GPU memory usage. With fixed prompts, steady-state throughput also reaches 67FPS on an RTX5080 and 58FPS on an RTX5070Ti. We demonstrate customizable shooter and driving games with engine-enforced mechanics, and release code, model weights, and low-poly game assets to support research and creation of playable game worlds.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27999
PDF
-
Adaptive Stopping of Streamed Reasoning for Language Model Agents
2026-10-20 10:24:30JunHyeok Oh, Byung-Jun LeeAbstract
Reasoning-enabled language model agents can incur substantial computation before acting, although the reasoning needed varies across decisions. Existing stopping signals, such as confidence and intermediate-answer stability, can vary in effectiveness across reasoning models; signals obtained from hidden states or token probabilities also require internal access that may be unavailable or impractical. We introduce StreamStop, which learns model-specific stopping policies offline from prefix-level action agreement. A frozen prefix reader encodes available reasoning text for a lightweight stop head, allowing stopping without access to the reasoning model's internal signals. We construct and publicly release a dataset of agent reasoning trajectories with prefix-level action annotations. These annotations compare each prefix action with the full-reasoning reference action, enabling offline comparison of stopping rules and exact expected-return optimization of a discounted action-agreement objective. Conditioning the head on the discount factor allows the agreement-token trade-off to be adjusted at inference without retraining. In closed-loop evaluations on WebShop and ScienceWorld, StreamStop achieves higher observed success than most validation-selected fixed-budget settings while using fewer reasoning tokens than Full thinking. On WebShop with Qwen3.8-27B, it uses 42% fewer reasoning tokens per episode with similar observed task success.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27981
PDF
-
Learning Reachability-Based Safety Representations for Real-Time Robot Navigation in Unknown and Dynamic Environments
Abstract
Safe robot navigation in unknown, dynamic environments requires more than geometric collision checking: a robot still far from an obstacle may be unable to avoid it because of its speed, orientation, or the obstacle's motion. Hamilton--Jacobi (HJ) reachability analysis captures this in a value function whose sign separates states that admit a safe continuation from those where collision is unavoidable, but computing it online for every newly observed environment is too expensive. This dissertation trains neural implicit representations offline on reachability solutions to give optimization-based controllers this information in real time. Since the value function never exceeds the constraint, it equals a directly computed constraint, such as a signed distance, minus a nonnegative dynamics correction. Learning only this correction keeps represented obstacles outside the predicted safe set despite approximation errors. The first two of five methods use the learned function as a terminal constraint in model predictive control, for static local environments and predicted obstacle motion. The next two use it as a barrier candidate in control barrier function safety filters, for static environments and, through pairwise barriers in relative coordinates, for a varying number of moving obstacles. Simulations and hardware experiments on ground and aerial robots show better collision avoidance than geometric and hand-designed baselines, especially for short horizons and moving obstacles. The fifth method replaces the grid-based offline solver, which limits the first four to low-dimensional models. For control-affine dynamics with polytopic inputs, the HJ Hamiltonian is maximized at a vertex, so a parallelizable tree search over vertex inputs can generate training labels. With a loss from the HJ variational inequality, these labels yield barrier candidates for systems with up to 13 states.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16522
PDF
