Knowledge
-
MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
2026-09-29 21:00:48Lukas Thede, Yash Kumar Atri, David Chen, Danielle Bitterman, Matthias Bethge, Tom Hartvigsen, Zeynep AkataAbstract
Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time, outdated knowledge can pose safety risks. Existing evaluations of knowledge integration focus on factual recall, offering limited insight into whether newly integrated knowledge is actually usable. Our benchmark MedKIT (Medical Knowledge Integration and Transfer) provides a granular evaluation of how models integrate and apply knowledge under realistic sequences of clinical updates. Each instance corresponds to a factual update derived from clinical evidence, paired with targeted probes that assess transfer across lexical variation, relational transformations, compositional reasoning, and open-ended operationalization, as well as locality tests for knowledge preservation. Using MedKIT, we conduct a large-scale empirical study of 12 knowledge integration strategies across 5 diverse models, including both general-purpose and medical LLMs. Our results reveal a consistent gap between recall and usable knowledge: while most methods achieve strong gains on the original update task and under lexical variation, relational generalization is limited, and no method yields meaningful improvements on compositional or operational tasks. These findings highlight a fundamental challenge in knowledge integration and position MedKIT as a testbed for developing methods that make newly integrated knowledge more consistently usable across tasks and contexts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38543
PDF
-
An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
2026-09-29 20:27:33Hadiza Umar Yusuf, Khouloud GaaloulAbstract
Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace analytically derived control laws, this occurs without a systematic understanding of how controller architectures differ or remain similar across paradigms. We address this gap with an empirical study of traditional and AI-enabled Simulink controllers, guided by a literature-derived taxonomy of ten structural categories and nine functional roles. The study analyzes 62 real-world models spanning 8 controller types and 10 application domains, and surveys 13 practitioners, identifying three architectural tensions. First, subsystem organization dominates all controller structures regardless of paradigm, occupying 68-72% of controller footprint, while core control logic occupies minimal space. Second, AI-enabled controllers rely heavily on discrete dynamics and user-defined abstraction, categories largely absent from AI literature, exposing a gap between described and implemented architectures. Third, constraint enforcement blocks largely disappear from AI-enabled models despite practitioner expectations. This reveals a misalignment where safety mechanisms shift from explicit structure to implicit training-time artifacts, breaking traceability.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38504
PDF
-
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
2026-09-29 20:22:29Yaozhong Shi, Zachary E. Ross, Yisong YueAbstract
Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow Annealing Posterior Sampling (FLAPS), to our knowledge the first function-space posterior sampling framework that unifies stochastic-process regression and PDE inverse problems. Built on pretrained function-space flow-matching priors, FLAPS enables likelihood-guided posterior inference from sparse and noisy observations, supports variable query discretizations, and avoids explicit prior-density evaluation. Its Langevin correction uses a low-rank covariance preconditioner to exploit dominant function-space correlations across discretizations. Across Gaussian and non-Gaussian stochastic-process regression benchmarks and diverse PDE inverse problems, FLAPS produces coherent posterior samples with well-calibrated uncertainty quantification, significantly outperforming existing functional regression baselines and achieving competitive or better noisy PDE inverse performance than diffusion-based posterior samplers while reducing test-time sampling cost.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22346
PDF
-
Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
2026-09-29 20:04:29Bhagyesh Rathi, Eshan Chawla, William B. AndreopoulosAbstract
Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is large and the trade-offs between variants are not well understood, especially on domain-specific corpora at realistic scale. In this work, we present a controlled comparison of six retrieval strategies for scientific question answering: (i) classic top-k dense retrieval, (ii) LLM-based query rephrasing, (iii) query rephrasing followed by LLM-based reranking, (iv) multi-query fusion via Reciprocal Rank Fusion (RRF), (v) an agentic tool-call pipeline in which the generator decides for itself whether to retrieve, and (vi) late-interaction retrieval with ColBERTv2. All six pipelines share the same generator (Meta-Llama/Llama-3.1-8B-Instruct), prompt, and evaluation protocol; the five single-vector pipelines additionally share SPECTER2 embeddings and a Chroma vector store; and all six retrieve from the full corpus of 463,971 arXiv papers dated 2024-2025. To support reproducible, large-scale evaluation, we also release a synthetic question dataset of 19,484 problem-statement and methodology questions generated by Llama-3.1-8B-Instruct from a random sample of 10,000 papers across academic domains (query generation succeeded for 9,742 of them), and every strategy is evaluated on this same query set. We describe the architecture and implementation of each pipeline, release the code and the synthetic question dataset, and evaluate each strategy with an LLM-as-a-judge protocol along multiple quality dimensions, together with direct gold-paper retrieval metrics. The result is an open testbed for studying the cost and quality trade-offs of RAG design choices on a research-literature corpus, and a basis for future work on faithfulness, retrieval robustness, and agentic retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38473
PDF
-
TACIT: Optimization Models that Learn from Their Mistakes
2026-09-29 19:26:53Maxime Bouscary, Marco Molinaro, Sirui Li, Saurabh Amin, Ishai Menache, Konstantina MellouAbstract
Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge, making them hard to formalize. As a result, optimization models often contain miscalibrated objectives, missing constraints, or omitted decision variables, leading to solutions that fail to reflect operational realities. We address this challenge by automatically repairing misspecified formulations using historical data consisting of past solutions and subsequent user overrides. Traditional approaches such as inverse optimization and constraint learning tend to overfit sparse data and produce complex formulations. Our central idea is to combine the reasoning capabilities and prior knowledge of LLMs with the formal grounding provided by optimization. We realize this idea through two complementary paradigms. Top-down, an LLM proposes structural repairs, including new constraints and variables, whose numerical parameters are calibrated and validated through optimization. Bottom-up, optimization infers cuts from observed decisions, which the LLM contextualizes into interpretable, generalizable modeling constraints. We evaluate our approach on 38 misspecification scenarios spanning nine classes of optimization problems, several drawn from real-world applications, and show that TACIT can repair 78.9% of them (vs. 60.5% for the best baseline).
Abstract (translated)
URL
https://arxiv.org/abs/2609.38434
PDF
-
VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding
2026-09-29 19:06:54Susan Liang, Jianmin Wu, Daxiang DongAbstract
Vision-language models (VLMs) can answer questions about hour-long videos, but processing every frame is prohibitively expensive, even though the evidence for a question usually spans only a few seconds. Video agents, i.e., harness programs wrapped around a frozen VLM, address this by observing the video selectively, yet existing harnesses are hand-crafted by experts through slow build-and-test cycles. We propose VidHarness, a framework that automates harness design for cost-efficient long video understanding, in which a harness proposer iteratively evolves harnesses based on execution feedback from an evolution environment. To escape the local optima of greedy refinement, we organize the evolution as Monte Carlo tree search (MCTS), and to reduce the evaluation cost, we integrate uncertainty-aware multi-fidelity validation, which screens new harnesses on a few questions and promotes only the promising ones. Since the best harness varies with the frame budget, we further introduce a mixture-of-harness that routes each question to a harness specialized for its budget. VidHarness sets new state-of-the-art results on LongVideoBench, Video-MME, and Video-Holmes, outperforms the strongest hand-crafted video agent by up to $11.2$ points, and generalizes to the knowledge-intensive benchmarks Video-MMMU and MMVU with fewer than half of the frames of uniform sampling.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38413
PDF
-
TALK-Dem: Benchmarking Embodied Task Planning under Dementia-Associated Communication Patterns
2026-09-29 18:33:21Guangxin Zhao, Yiran Hu, Yuan Cao, Chenxi Jiang, Jianfei Yang, Yegang Du, Yasuyuki Taki, Yoshifumi Kitamura, Lin Gu, Zhi ZhengAbstract
Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focused. However, when interacting with real-world users, especially those experiencing cognitive impairments, such as people living with dementia (PLWD), the planners often make mistakes and even pose physical safety risks. We proposed TALK-Dem (Talking Attributes and Linguistic Knowledge in Dementia), the first benchmark for evaluating LLM-driven robot task planning under dementia-associated verbal communication. TALK-Dem contains 4,800 instructions and covers five typical communication patterns, including Referential Imprecision, Object Substitution, Empty Speech, Topic Drift, and Intrusion, at three intensity levels. Experiments across six open-weight LLMs reveal a substantial robustness gap. Across communication patterns, open-weight models exhibited performance drops of up to 22.3 percentage points compared to ideal instructions. This revealed a critical gap and even danger for real-world applications, especially in assistive robotics, where locally deployable models are necessary due to privacy concerns and connectivity constraints. To mitigate this issue, we proposed the Context-Aware Retrieval from Experience (CARE) method, which retrieves relevant previously resolved tasks to provide task-specific interpretation and planning context. CARE generally outperformed standard prompting baselines across the six open-weight models, improving average task success by 18.1 percentage points over the vanilla prompt. These results highlighted the importance of both evaluating communication robustness and developing effective adaptation strategies for locally deployable assistive robots. The TALK-Dem dataset is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38371
PDF
-
Can an AI Agent Rediscover a Blaschke-Curve Invariant?
Abstract
We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an agent receives numerical coordinates of the six pair-lines determined by each of 80 boundary configurations. The target theorem is withheld from the task instructions. The saved research log reports rejected geometric hypotheses and a homogeneous cubic fitted to polygon sides. Its frozen coefficients predict 480 lines from 80 unseen parameter values, with a recorded RMS scale-free residual of $8.88\times10^{-17}$. Discovery-set diagonals provide an out-of-fit consistency check, not a fully held-out test. A separate one-configuration run reports insufficient evidence for invariance. A post-review deterministic degree-search baseline also recovers the cubic, so the experiment does not establish an advantage over polynomial fitting. We present this single-instance case study as a protocol for separating conjecture, numerical validation, and proof, with explicit limitations concerning agent metadata, prior knowledge, and reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38369
PDF
-
Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs
2026-09-29 18:25:04Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang, Po-Hsiang Hsu, Li-Yu Chen, Chun-Yi Lee, Min SunAbstract
Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining distribution, yet fail on specialized domains where the required discriminative features were never learned, a regime we term distant out-of-distribution (OOD). Standard adaptation methods cannot overcome this representational absence because they operate within the encoder's existing feature space. However, VLMs retain a robust descriptive capacity even when discrimination collapses: a model that cannot classify a medical scan can still articulate its visual patterns. Exploiting this asymmetry, we introduce Inductive Visual Logic (IVL), a training-free framework that constructs classification knowledge from the model's surviving descriptive ability. IVL extracts visual traits from few-shot support images through dual-mode prompting, combining semantic descriptions with primitive visual observations, and organizes them into per-class trait dictionaries. At inference, hierarchical filtering identifies spatially grounded trait evidence for classification. Across multiple distant-OOD benchmarks, IVL achieves the highest aggregate accuracy under two VLM backbones while producing interpretable, trait-traceable predictions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38362
PDF
-
Halluscoring 2026: The first shared task on llms hallucination detection and answer verification
2026-09-29 18:18:18Aisha Alansari, Abdessalam Bouchekif, Ahmed Hasanaath, Salah Eddine Bekhouche, Malak Alkhorasani, Mohammed-En-Nadhir Zighem, Saad Ezzini, Hichem Telli, Hend Al-Khalifa, Muhammad Abdul-Mageed, Hadid Abdenour, Hamzah LuqmanAbstract
We present HalluScoring 2026, a shared task for evaluating hallucination detection and factual verification in Arabic question answering under challenging generalization settings. The shared task is organized into two main tasks, each comprising two subtasks, for a total of four subtasks. Task 1 evaluates binary hallucination detection, considering generalization to unseen questions (Subtask 1.1) and responses generated by unseen LLMs (Subtask 1.2). Task 2 extends the evaluation beyond detection by requiring the systems to additionally identify the correct factual answer from six related candidates, covering Islamic knowledge (Subtask 2.1) and general knowledge (Subtask 2.2). The shared task is based on two Arabic datasets: HalluScore and HalluTruthQA. A total of 13 teams participated in the shared task, 10 of which submitted system description papers. The results of Task 1 demonstrate that hallucination detection remains challenging under distribution shift, with the winning team achieving AUC-ROC test scores of 0.772 and 0.767 for Subtasks 1.1 and 1.2, respectively. For Task 2, the winning team achieved scores of 0.882 and 0.857 in the Islamic and general-knowledge subtasks, respectively, under assisted evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38355
PDF
-
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
2026-09-29 18:01:45Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li, Jianguo Huang, Zhicheng Wang, Hu Zhu, Qiuyu Chen, Yuntao Wei, Xin Jin, Wenjun ZengAbstract
Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training and errors that compound when predictions are used for planning. However, for LLM agents operating in digital environments, much of this world knowledge is already internalized during pretraining, which shifts the problem from acquiring it to eliciting it. We argue that typical post-training provides little pressure for such elicitation, since supervision under a single goal at each visited state inadvertently drives policies to rely on superficial contextual habits. We introduce EVOKE, a post-training method that supplies this pressure through goal diversity at fixed states. Motivated by theory showing that an agent competent across diverse goals must encode a world model recoverable from its action preferences, EVOKE holds the environment state and interaction history fixed and ranks the same candidate actions under alternative goals, forcing action preferences to change, so that a policy relying on contextual habits or single-goal correlations cannot order them correctly. This implicitly elicits the policy's pretrained world knowledge to inform decisions. We evaluate EVOKE across diverse tasks in three backbones, demonstrating improved task performance, unseen environment generalization, and data efficiency. We further conduct controlled analyses to better understand what drives these gains. These findings offer a new perspective on eliciting internalized world knowledge for transferable action through direct decision supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38334
PDF
-
Searching for BSM Experimental Signatures with Large Lagrangian Models
2026-09-29 18:00:01Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji, Aishik GhoshAbstract
The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating experimental observations. A case in point is dark matter, where the overwhelming gravitational evidence only goes so far in distinguishing between models within a vast theory space. Exploring the space of testable model signatures may help identify overlooked experimental observables and indicate the utility of future experiments. A challenge is designing a search through model signatures outside what is found in the literature. Our primary contribution is hAIthem, a framework that combines the self-guided exploration of reinforcement learning (RL) with the broad literature-derived knowledge of LLMs. We build an RL agent that learns to find which portions of a theory's high-dimensional parameter space are not excluded under some subset of constraints by playing a Battleship-style "game" against a suite of phenomenology tools. The agent is built as a Large Lagrangian Model (LLaM), an autoregressive transformer that reads a tokenized Lagrangian, is pretrained at scale (here on ~1 billion tokens from ~10,000 Lagrangians), and is fine-tuned in a live environment. The framework then constructs a decision tree that separates RL-found regions using observables computed with established tools, and passes the remaining degenerate regions to a set of LLM agents that compete to produce realistic signatures. In this proof of concept, RL-search outperforms an evolutionary-algorithm baseline, finding more viable regions with greater physical diversity. In a restricted space of single dark scalar multiplet models, we find that hAIthem proposes interesting combinations of previously studied observables, such as the application of a halo-independent kinematic ratio to paleo-detectors.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38309
PDF
-
Adversarial Training for Pixel Diffusion
2026-09-29 17:59:41Xin Lin, Zhifei Zhang, Yuqian Zhou, Haitian Zheng, Zhe Lin, Ming-Hsuan Yang, Truong NguyenAbstract
Pixel diffusion models generate RGB images directly, avoiding the bottleneck of an autoencoder, yet their outputs still systematically underrepresent fine-scale natural-image statistics. We show that adversarial learning provides an effective post-training correction for this deficiency. Starting from a pretrained model, we retain its original diffusion or flow-matching objective and add an adversarial loss to the predicted output at non-high-noise timesteps, leaving the model architecture and sampling procedure unchanged. To our knowledge, this is the first systematic study of adversarial post-training for pixel diffusion. Across two pixel backbones, the method jointly improves distribution fidelity, coverage, prompt alignment, and perceptual quality. We further investigate why it works. Frequency-band and power-law analyses show that the original models systematically underproduce natural-image high-frequency content, while adversarial post-training restores this missing spectral power. In contrast, perceptual loss also increases high-frequency content but sacrifices distribution fidelity and prompt alignment. Nearest-neighbor, recall, and matched no-GAN SFT controls further rule out memorization, mode dropping, and additional optimization as simple explanations. Finally, we examine the boundary of this effect. Under the tested latent diffusion configurations, the same procedure does not produce comparable joint gains and adds almost no decoded high-frequency power. These results identify direct output access to the image statistics being corrected as a key factor governing when adversarial post-training succeeds.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38170
PDF
-
FORM: Robot Manipulation through Direct Material Law Identification
2026-09-29 17:46:40Stepan Tretiakov, Ruihan Zhao, Cheng-Hsi Hsiao, Xingjian Li, Adam Thorpe, Hassan Iqbal, Sandeep Chinchali, Ufuk Topcu, Krishna KumarAbstract
When interacting with an unfamiliar deformable material, a robot lacks prior knowledge of its physical properties and how it will respond to applied forces and motion. Rapid online identification is therefore essential for reliable manipulation. We present FORM (From Observed Response to Material laws), which identifies material properties from a single robot interaction and reuses the recovered model to plan manipulation under new actions and geometries. We use weak-form momentum balance to convert observed material motion and contact forces into linear equations in the unknown material parameters. These equations are assembled using the same material point method discretization as the forward simulator, so identification reduces to linear least-squares solves whose solutions can be used directly for prediction without refitting or conversion. Across four material classes, FORM reduces identification time from roughly 10--25 minutes for iterative baselines to 2--5 seconds, while maintaining competitive accuracy on new motions, initial conditions, and geometries. We demonstrate our approach in simulation and on hardware across four manipulation tasks: elastic rod insertion, golf putting with an elastic club, elastoplastic shaping, and target-volume pouring. In each task, the model identified from a single interaction is reused to plan new motions or manipulate a different geometry. FORM estimates elastic properties within 3.4% and elastoplastic properties within 2%, achieves 72.4--77.8% IoU in dough shaping, and keeps mean pouring error at 3.8 mL across target volumes of 60--160 mL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38105
PDF
-
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
2026-09-29 17:36:40Bingxuan Li, Siqi Song, Yizhuo Wu, Jiarui Yao, Tong Zhang, Huan ZhangAbstract
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized training keeps them from benefiting directly from rapidly advancing general-purpose vision-language models (VLMs). In parallel, recent agentic robotic systems leverage VLMs for high-level reasoning or coding agents for robot control, but often depend on extensive external models and tools, introducing additional complexity and cost. This motivates us to ask: Can a general-purpose VLM itself operate a robot more like the human teleoperator by reasoning directly from observations, issuing actions, and continuously adapting to execution feedback, without relying on external models such as learned action experts, coding agents or grounding tools like SAM3? In this work, we introduce MotorMind, a robot manipulation harness that connects VLM-proposed mid-level actions to deterministic robot control and feedback, with asynchronous monitoring and background memory updates. Without task-specific policy training, coding agents, or additional grounding tools such as SAM3, MotorMind achieves 66.7% success on the base LIBERO-PRO suites and 53.8% under perturbations, compared with at most 13.3% and 19.2%, respectively, for the prior zero-shot methods we evaluate. The same interface reaches 95% average success on a real xArm6 robot across direct manipulation and human-perturbation settings. Replacing the backbone with a stronger VLM further improves performance, while the remaining failures - primarily due to visual grounding, embodied reasoning, and action knowledge - decrease as VLM capability improves. These results show that a general-purpose VLM, when equipped with an appropriate mid-level action representation and asynchronous execution harness, can perform effective zero-shot robotic manipulation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38078
PDF
-
A QCQP-Representable IMU Pre-Integration Factor for Certifiable State Estimation
2026-09-29 17:19:54Utkarsh Rai, Zhexin Xu, Bang-Shien Chen, David RosenAbstract
We propose a QCQP-representable IMU pre-integration factor that enables certifiable estimation with pre-integrated inertial measurements. To the best of our knowledge, this is the first work to directly incorporate IMU pre-integration into certifiable estimation. Inertial sensing is a common and reliable modality in robotics, and incorporating it broadens the practical scope of certifiable estimation. The main challenges are obtaining the required algebraic structure and a sufficiently tight convex relaxation. Standard IMU pre-integration relies on the exponential map, which does not admit an exact polynomial representation. Moreover, obtaining a QCQP formulation requires auxiliary lifting variables, for which the standard semidefinite programming (SDP) relaxation can be loose. We address these issues by deriving an IMU pre-integration factor based on the Cayley map and an explicit set of redundant constraints that tighten the resulting relaxation. To validate the proposed factor, we apply it to certifiable GNSS-IMU smoothing and evaluate it on synthetic and real-world data. The results show that the proposed formulation yields tight relaxations and solves the resulting estimation problems to verified global optimality.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38048
PDF
-
doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
2026-09-29 17:08:01Parthib Roy, Yash Tandon, Marcus Blennemann, Giovanni Tapia Lopez, Angel Martinez-Sanchez, Mohan M. Trivedi, Ross GreerAbstract
Autonomous vehicles interacting with passengers through natural language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, depend on future events, refer to surrounding agents or landmarks, and remain relevant as driving conditions evolve. Existing language-enabled driving datasets largely focus on short, localized interactions, leaving these longer-horizon forms of passenger intent comparatively underexplored. We introduce doPlan, to our knowledge the first publicly available, human-annotated real-world dataset designed to study passenger language as persistent task context. Built on nuPlan, doPlan contains 5,154 human-written passenger instructions spanning 169.1 hours of cumulative instruction-aligned context over 50.9 hours of unique driving, with annotation windows ranging from 30.0 to 508.8 s. The annotations capture immediate, deferred, event-conditioned, persistent, and multi-stage passenger intent. The dataset, annotation interface, and supporting resources are publicly available at this https URL. We evaluate four language-conditioned driving models and find that sensitivity to passenger language does not reliably translate into behavior consistent with the requested direction. More broadly, among 2,161 examples with a matched future maneuver, the first associated maneuver occurs a median of 24.6 s after the evaluation point, and only 9.8% occur within the models' common 5 s prediction horizon. These findings highlight the need to connect persistent passenger intent with successive planning decisions. doPlan provides a setting for studying how unresolved goals can be retained, grounded in evolving scenes, and tracked across multiple stages, including how a planner determines when a future goal becomes relevant to the current plan.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38028
PDF
-
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
2026-09-29 17:06:43Jaewon Chu, Ji Soo Lee, Jihwan Park, Dohwan Ko, Jeehye Na, Seunghun Lee, Taehoon Lee, Minseo Yoon, Minseok Joo, Yunyang Xiong, Hyunwoo J. KimAbstract
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbf{Retrieval-Augmented Skill Optimization (RASO)}, a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbf{Retrieval-Augmented Skill Initialization (RASI)} constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbf{Retrieval-Augmented Skill Update (RASU)} iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38024
PDF
-
Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S
2026-09-29 17:04:18Christopher J. ChanhnourackAbstract
We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, coverage-first packet compilation, and deterministic reasoning scaffolds; an LLM is used only as a replaceable final reader. The chain places all gold sessions in the candidate pool for 468/470 answerable questions and produces gold-complete packets for 462/470. With a Claude Opus reader called through an unpinned CLI alias, two 500-question passes score 479/500 and 475/500 under GPT-4o. The 72 answerable knowledge-update rows used a substantively modified scoring prompt whose effect under the official text has not been measured. The pair straddles Chronos High's published 478/500; differences in reader generation, scoring prompt, and possibly data version, plus within-system variance, establish neither superiority nor equivalence. A grok-4.6-high reader on the same packets scores 476/474, while a maximum-reasoning-effort agentic variant regresses to 461/465. The headline passes differ on eight verdict-flip rows. A second judge agrees with the headline judge on 493/500 rows (98.6%) in each pass and scores both passes 472/500; the official judge also flips three verdicts when re-scoring byte-identical pass-1 answers. Negative controls rejected a verifier that repaired three wrong drafts but broke eleven correct drafts. All components were developed on the same 500 questions, with no held-out evaluation or independent human adjudication; retrieval and scaffold method sources and transcript-derived audits are held; and the headline reader received extra operator context, its complete requests were not retained, and MCP tool availability is unresolved. We release materialized packets, scaffolds, reader outputs, judge verdicts, and controls for inspection and re-scoring.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38021
PDF
-
Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
2026-09-29 16:39:26Ying Song, Xiaowei Jia, Balaji PalanisamyAbstract
As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By querying a victim model's black-box API, an adversary can construct a functionally equivalent surrogate model, compromising proprietary intellectual property and downstream security. Existing GNN stealing attacks, however, rely on overly permissive assumptions, such as soft-label outputs, large query budgets, full-graph query access, and prior knowledge of victim backbones that rarely hold in real-world deployments. In this work, we formalize a strictly constrained black-box, hard-label and backbone-agnostic threat model for GNN stealing attacks under a tight query budget. Given these realistic restrictions, we identify four fundamental challenges: sparse local structures and isolated nodes that degrade victim label quality, insufficient supervision signals, systematic imbalance with incomplete class coverage, and backbone mismatch. To address these interlocking barriers, we propose Dagger, a novel two-phase decoupling-based attack framework. Specifically, in Phase 1, Dagger pre-trains a surrogate using decoupled information propagation to preserve structural context over sparse local subgraphs while handling isolated nodes, combined with manifold-level node mixup to synthesize continuous supervision signals and smooth decision boundaries. In Phase 2, Dagger freezes the encoder and fine-tunes the classifier head via class-balanced sampling paired with logit adjustment to rectify severe query imbalance without requiring extra victim queries. Extensive experiments across four benchmark graphs and four GNN backbones demonstrate that Dagger consistently outperforms state-of-the-art GNN stealing attacks, achieving up to 18.16\% higher fidelity while only utilizing 12.23$\times$ fewer queries than the strongest baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37972
PDF
