Object counting in videos remains a poorly characterized capability of multimodal large language models. Counting questions are included in many existing VideoQA benchmarks, but the ground-truth count distributions in these benchmarks are heavily skewed toward small values. Across the nine benchmarks we survey, the median ground-truth count is at most five, and the three most frequent values together account for between 45% and 93% of the videos. The resulting mean accuracy is then dominated by the most frequent counts; a value-dependent bias at a rare count contributes negligibly to the average and remains invisible. We introduce CountVideoBench, a benchmark of 2,600 synthetic videos covering 26 cardinalities in the interval [5, 50] (100 videos each), grouped into six clusters of consecutive counts that span the range while enabling near-neighbor comparisons. Each video contains a single class of static objects under a controlled camera motion, removing object motion and reducing recognition as confounds. We evaluate sixteen video-language models from nine architecture families in a zero-shot setting. No model exceeds 27.6% Exact Match. The dependence of accuracy on cardinality varies across models, ranging from monotonic decline to a non-monotonic peak-and-collapse pattern, which rules out increasing difficulty with cardinality as the dominant explanation of counting failure. Every model further concentrates its predictions on its own set of preferred integers, with accuracy peaks coinciding with these values and collapsing at adjacent counts. These findings highlight the need for balanced, diagnostic counting benchmarks to reliably assess this fundamental visual capability.
https://arxiv.org/abs/2610.28356
The rapid growth of scientific literature makes survey writing increasingly challenging, motivating automatic survey generation. Yet, existing systems must search an open space of papers and an open space of concepts with no trace of how the community itself has navigated them, leading to incomplete scope, weak taxonomies, and unreliable citations. Our core insight is that author-written Related Work sections contain the human judgments needed to address both limitations: authors curate the citations relevant to their contributions and explain how the cited works relate, yielding paths for scope reconstruction and relational evidence for organization. We propose InsightRAG. Its insight-guided retrieval follows author-supported citation relations to reconstruct a verified research scope and structure the resulting relational evidence. It aggregates these judgments under a minimum-conflict objective into a taxonomy that reflects recurring author-written perspectives in the retrieved literature, guides generation, and bounds each section's evidence. Results on ten topics show gains in scope reconstruction, taxonomy quality, citation support, and reference reliability.
https://arxiv.org/abs/2610.28085
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.
https://arxiv.org/abs/2610.28699
Mountain glaciers and ice sheets are undergoing rapid loss of ice mass. To assess their current volume and ice-thickness distribution, and to accurately forecast their future, ground-penetrating radar systems are employed to measure ice thickness. These instruments produce radio-echo sounding data that reveal the internal structure of the ice and its boundaries at the surface and beneath the ice body. However, delineating these interfaces is time-consuming as the surveyed area can span several hundred kilometers. To accelerate the labelling process, automated methods have emerged, but they often struggle to delineate the ice bottom, particularly in temperate glaciers. The high water content inherent in temperate ice increases both scattering and attenuation of the radar signal, resulting in weak and ambiguous reflections at the ice bottom and generally noisier data. As a result, the visual features corresponding to the ice bottom become ambiguous. To address this issue, we propose several extensions to deep learning models that incorporate additional contextual information into the prediction. Specifically, we integrate modifications that incorporate additional spatial and geo-spatial contextual information into the network. With these enhancements, we achieve a new state-of-the-art performance on the IceAnatomy benchmark dataset, with mean errors of 10.9 m for the FAU subset and 43.4 m for the CReSIS subset in a single combined system. We also demonstrate that our method generalises well to previously unseen data, outperforming the baseline by 49.6 % on new campaign data from Patagonia. The model code and the new dataset are available at this https URL and this https URL.
https://arxiv.org/abs/2610.27912
Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic household personas grounded in real-survey data. Its Genese engine separates decisions from state updates, while reusable financial scenarios and application ledgers track consumption, cash, debt and payments. FinL-mlx, a compact decision model trained with SFT + RLCD on 2.93 million examples, achieves 74.55% accuracy and 38.37% question-macro F1 in consumer financial-choice scenarios, outperforming Jev 1.13 and GLM-5.3-Flash on both measures. We evaluate eight financial task families and simulate 12 million distinct household agents in paired purchase-funding conditions. Jointly raising purchase goals and approved credit limits increases consumption, with responses differing across age and income groups. Education, employment and household-size differences persist after age--income standardization and mainly reflect transitions from deferral to purchase. Asset and debt groups differ in cash drawdown, repayment and closing debt. A 24-month panel varies purchase goals under a common credit product, with repayment and arrears updating subsequent offers. S$^2$-MAS links heterogeneous household decisions to evolving consumption, cash and repayment paths, supporting economic experiments across household groups, population scales and time horizons.
https://arxiv.org/abs/2610.27746
Recent work reports that the distribution verbalized directly in the output text aligns far better with human opinion distributions than the next-token log-probability distribution of LLMs. However, the verbalized distribution reflects what LLMs know about a group's opinions (knowledge distribution), while what they actually output at deployment is governed by their log-probability distribution (behavior distribution). We find that when prompting LLMs to predict the opinion of a specific group, the most likely answer under the verbalized distribution differs from that under the log-probability distribution for 37% of World Values Survey questions, averaged over three LLMs. Thus, LLMs' knowledge does not match their behavior. This matters for evaluation: a verbalized distribution can score well against a group while its most likely answer is one the model never outputs, so the score no longer describes the model. The alignment scores for these two distributions reflect only the model's behavior or its knowledge, separately. We therefore propose a learnable combination of the two distributions that follows the most likely answer of the behavior distribution while preserving the shape of the knowledge distribution, with a single hyperparameter trading off behavioral fidelity against distribution quality. Our experiments on three opinion survey datasets and six models show that the balanced distribution improves behavioral consistency over the verbalized distribution from 71.6% to 95.6% on average, while the total variation distance to the human opinion distributions rises only slightly from 28.8% to 33.8%, and it remains effective under temperature scaling and cross-dataset settings.
https://arxiv.org/abs/2610.27648
Systems for code-mixed (CM) text and speech rarely start from scratch. CM data is scarce, so most work borrows from the languages being mixed, which we call native languages. This transfer can also run in reverse, when CM data is used to improve models for the native languages. Existing surveys focus on processing CM itself, and none brings the two directions together. This paper fills that gap with a systematic survey of transfer in both directions, across text and speech. We organise the surveyed work in a taxonomy of transfer direction, route and modality. Through this taxonomy, we find that most transfer runs from native languages into the CM setting. The reverse direction is younger, and in it code-switching mainly helps by aligning the two languages. Text and speech work share methods but rarely cite each other. On a shared speech benchmark, native data helps more than new architectures. These findings point to open challenges, such as how much native and CM data to mix in training, and how to evaluate CM text written in different scripts.
https://arxiv.org/abs/2610.27631
We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on the adversarial split, sat 1.21 to 8.67 points above the adversarial baselines we planned to compare against (81.00, 79.30, and 73.54). We looked at the evaluation code and found a readout choice that moves F1 on its own. A two-token logit readout decides yes versus no by comparing two vocabulary IDs, 3582 ("yes") and 1217 ("no"). Across 9,000 greedy-decode questions spanning all three splits, neither ID is generated even once. The model emits " Yes" (token 3869) and " No" (token 1939), because SentencePiece prepends a space byte after the prompt suffix "ASSISTANT:". Read with an eight-token lookup that covers the space-prefixed surface forms, LLaVA-1.5-7B scores F1 0.8221, 0.8498, and 0.8713 on the adversarial, popular, and random splits. That 6.13-point adversarial shift exceeds the adversarial gain reported by five of the six papers we surveyed. None of them states its readout, and our reference ran under 4-bit NF4 quantization, so we cannot say how much of any reported gain a matched evaluation would keep. That comparison stays unresolved until readout and precision are matched. On the fixed baseline we run nine inference-time corrections of our own (none beat it) and dissect why the adversarial split resists logit-level intervention. In a 3,000-question probe, wrong predictions draw more image attention than correct ones (Cohen's $d=-0.46$, $p=1.4\times10^{-24}$), the opposite of what grounding-based corrections assume. A four-readout audit across four further VLMs from three tokenizer families confirms the confound is protocol-level, not model-specific: porting the LLaVA-1.5 IDs verbatim drops F1 to 0.00 on the two disjoint-vocabulary models, whereas a tokenizer-derived readout holds between 0.80 and 0.92.
https://arxiv.org/abs/2610.25964
Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a locally authorized execution, or a pair of locally authorized executions, that violates a global policy spanning intent, purpose, provenance, consent, and delegation. We characterize CAFs along two axes, expressiveness (single-trace safety versus relational k-safety) and observability (a ladder of monitor profiles). Our central result is an impossibility: relational purpose violations form a 2-safety hyperproperty with no per-trace locus of blame, so a per-action monitor that never raises a false alarm detects none of them, independent of the underlying model or decision procedure; they become visible only under cross-execution monitoring, which none of the six guardrails we survey implements. We make this constructive with AL-SYNTH, a SAT/SMT synthesizer (using no language model) that emits minimal CAF witnesses, each checked against an exhaustive oracle. The empirical signature is sharp: across nine LLM judges the per-action view approves the synthesized witness almost without exception, blocking it at a rate comparable to a benign control, yet the same models flag it when shown the two executions together. Per-action authorization is therefore structurally insufficient for relational policy conjuncts not reducible to single-trace safety: to bound them, a monitor must compare executions or accept false alarms.
https://arxiv.org/abs/2610.27620
Recursive self-improvement (RSI) promises AI systems, such as self-evolving LLM agents, that become better at producing further improvements. Evaluating this promise requires separating product claims about the final system from process claims about the improvement process itself. Existing surveys specify the evidence these claims require, but how often studies report that evidence remains unmeasured. We examine this question through full-text coding of 114 eligible studies in a reproducible arXiv search frame frozen in October 2026, including 90 that describe their own systems as RSI. The codebook links claims to evaluation designs. Independent human coding, third-reader adjudication, and a separate blind coding of improver comparisons assess coding reliability. Among the 90 RSI studies, 90% report product evaluation beyond development tasks under a broad criterion that includes partial or unstated separation, while 60% report evaluation on tasks unused for selection. Only 22% audit two or more reruns of the full loop. In a human-coded random sample, the RSI studies show the same contrast: 45% evaluate on tasks unused for selection and 14% audit two or more reruns. Of the 26 studies claiming a better improvement procedure, 23 report a related comparison, but only 4 compare earlier and later procedures from identical starting artifacts at a matched budget. Across these results and a comparison set of established works, evidence for repeatability and improved procedures remains less developed than product evaluation. Three propositions explain how selection effects, shared evaluator errors, and changes in system state limit what product evaluations can establish. Together, the findings support a claim-indexed reporting standard that connects each claim to the evaluation design needed to test it.
https://arxiv.org/abs/2610.27610
In real-time autonomous field applications, GNSS is often unreliable and inaccurate. A possible solution is localizing against a prebuilt map like a satellite image, as it is georeferenced and already surveyed. In this work, we localize a spinning radar measurement against overhead RGB imagery with a learned observation model. We use a radar representation pretrained by masked reconstruction and align it to features from a satellite image. A particle filter propagated by radar odometry proposes candidate poses, and our observation model provides a likelihood over these poses. We evaluate our method over 31 distinct routes, over 8 datasets spanning both urban and offroad conditions using only ground radar and a coarse local prior. We also examine the robustness over changing weather using repeated traversals over the same route over 13 months, in both urban and offroad conditions.
https://arxiv.org/abs/2610.27310
Face recognition systems have been ubiquitously deployed across daily scenarios. To protect user privacy, mainstream systems store facial templates rather than raw face images for identity verification. However, facial template inversion (FTI) technologies can reconstruct faces from templates, which endangers biometric privacy. Existing FTI methods only fit single type of templates, failing to reconstruct identity-consistent faces from unseen types. To tackle this limitation, we survey mainstream template extractors which can be classified into five categories according the template distribution: unit-sphere, angle-linear, strict unit-sphere, cone-shaped, anuniform hypersphere. Inspired by this observation, this paper proposes GMoE-FTI, a universal FTI framework powered by a genuine MoE mechanism that differs from load-balanced multi-branch alternatives. It follows a three-stage training strategy: (1) independently train five mapping experts (MEs) and a matching module (MM); (2) conduct collaborative inference by weighting each ME's output with MM's output, so as to generate unified latent codes compatible with pre-trained StyleGAN3; (3) perform end-to-end joint fine-tuning over all modules to identity consistency and boost cross-expert coordination. Extensive evaluations on the LFW benchmark validate the superiority of GMoE-FTI against SOTA methods. Evaluated on seven prevailing unseen template types including AdaFace, CosFace, CurricularFace, ElasticFace, SphereFace2, SphereFace-R, and TransFace, GMoE-FTI achieves an average 40% TAR improvement, with average FAPD and FAPC each reduced by 2%, verifying its universal generalization across heterogeneous templates.
https://arxiv.org/abs/2610.33055
Robotic systems for environmental monitoring and ecological surveying in wetlands and swamps must operate across diverse terrestrial and aquatic conditions. Conventional fixed-geometry wheels cannot adapt their contact geometry to these varying conditions. This work presents MOSS (Multimodal Origami Swamp Robot System), a compact amphibious robotic platform with 3D-printed origami wheels. The compact crank mechanism switches the wheel between contracted and expanded configurations, changing its width, body diameter, and fin orientation simultaneously. The contracted configuration is better suited to efficient rolling on firmer ground, whereas the expanded configuration provides greater contact and terrain engagement on softer surfaces. MOSS was evaluated on soil, sand, mud with varying water content, and water, in addition to in-motion morphing and terrestrial-aquatic transition tests. The more energy-efficient wheel configuration depended on terrain. The contracted configuration achieved a lower cost of transport on firmer soil and mud, whereas the expanded configuration performed better on wetter mud, sand, and water, reducing the cost of transport by up to 29%. Expanded wheels also reduced slip in wet mud and reduced both slip and hub sinkage in sand. MOSS successfully completed configuration changes in $1.95 \pm 0.11$ s and demonstrated continuous locomotion across soil-mud-water transitions. Outdoor trials further demonstrated operation across natural deformable terrain and water. These results show that adaptive wheel geometry provides terrain-dependent locomotion benefits and enables a single compact platform to traverse substantially different terrestrial and aquatic conditions.
https://arxiv.org/abs/2610.23813
Personalizing a language model requires knowing what a person values, which stays largely consistent across tasks. Yet most methods either learn task-specific preferences or place the user's profile in the prompt, where models struggle to act on it. We introduce VISTA (Value-Informed Steering and Targeted Acquisition), which infers a latent profile from users' (full or partial) survey answers, and maps the profile through a hypernetwork to a user-specific steering intervention in a frozen LLM to select answer choices or generate free-text responses. Given the same evidence, VISTA matches or beats in-context profiles on synthetic preferences (Food2D), the World Values Survey (WVS), and PrimeX, without adding prompt tokens. To reduce the cognitive burden of completing full surveys, VISTA also chooses which questions to ask and when to stop: on WVS it stops after 6% of the questionnaire while retaining 94% of the full-history gain, where standard adaptive testing retains at most 42%. The dominant steering direction is an interpretable value axis on which VISTA places unseen users accurately. Our results point toward pluralistic alignment that adapts to individuals at deployable cost.
https://arxiv.org/abs/2610.23702
This research investigates the role of artificial intelligence (AI) in modern compositional practices, with a particular focus on two case studies: Convergence (2020/21) by Alexander Schubert, for String Ensemble and AI System, and In Human Memories (2024) by Francesco Vitucci, for four cellos and one electroacoustic player, whose installation was created by the Electronic Music School of the "N. Piccinni" Conservatory of Bari. The initial historical survey traces the evolving use of technology in composition, revealing how the search for new expressive possibilities has driven the development of technological tools through experimentation. The appearance of AI marks a fundamental shift: no longer just a tool, AI now poses questions and challenges to the composer. Engaging with AI becomes an exploration of an unknown entity, whose full capabilities are still largely undiscovered. This new interaction leads composers to confront AI not merely as a passive resource but as a participant in the creative process, outlining an ethical path to reclaim technology as a creative tool. In Human Memories reflects this dynamic, demonstrating how AI can serve as both inspiration and a driving force in shaping contemporary music.
https://arxiv.org/abs/2610.23651
Long-horizon robotic tasks expose a fundamental limitation of current Vision-Language-Action (VLA) models because their restricted temporal context pre-vents effective accumulation and reuse of past experiences. As a result, memory has become a fundamental component for enabling embodied agents to perform long-horizon reasoning and adaptive decision-making. This survey presents a systematic taxonomy of VLA memory mechanisms based on memory scope and persistence, categorizing existing approaches into five representative paradigms and one emerging frontier. Based on this taxonomy, we compare representative VLA memory systems in terms of memory characteristics, architectural com-plexity, and open-source maturity, revealing a clear trade-off in which increasing architectural complexity is generally accompanied by decreasing open-source ma-turity. Finally, we discuss the key challenges in building full-lifecycle memory systems, including efficient memory management and lifelong knowledge evolu-tion. Overall, this survey provides a unified perspective on memory architectures for VLA agents and offers insights into the development of lifelong embodied in-telligence.
https://arxiv.org/abs/2610.23319
Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. However, in network formation tasks, existing evaluations often focus on aggregate network properties, while networks with plausible structural properties may still fail to reproduce individuals' social and political environments. Here, we generate LLM-based political networks using personas sampled from the nationally representative ANES 2020--2022 Social Media Study and use respondents' survey-reported partisan exposure as an empirical benchmark for the political environments generated for the corresponding personas. We first characterize the structural properties and political assortativity of the generated networks, and then compare ego-level partisan exposure with the survey. We find that the structure and political assortativity of the generated networks vary across experimental configurations. More importantly, when comparing generated partisan exposure with the survey, some models generate stronger separation between Democratic and Republican egos than reported in the survey, with higher same-party and lower cross-party exposure, while others mainly underestimate Republican exposure across ego groups. Moreover, networks with similar political assortativity can still generate different partisan environments around the same personas, including among networks with plausible structural properties. Finally, generated networks show group-specific errors, under- or overestimating exposure to either Democrats or Republicans for specific social groups. These findings show that evaluating LLM-based social simulations only through aggregate outcomes can hide errors in the local environments through which those outcomes emerge, highlighting the importance of validation at both aggregate and individual levels.
https://arxiv.org/abs/2610.23199
Assessing whether qualitative responses collected from semi-structured questions are ready for a particular analysis goal is a persistent challenge. Manual qualitative analysis is interpretive and labor-intensive, while existing automated methods often lack a dataset-level perspective for deciding whether a response set supports a researcher-selected analytical lens. We introduce QuAD, a framework for quantitative pre-analysis assessment of qualitative response datasets. QuAD compares a reconstructed intrinsic cluster distribution reconstructed from responses with an extrinsic, researcher-defined analytical lens derived from metadata. QuAD is structured into a four-quadrant assessment whose metrics are read jointly, from lens-level relations to within-cluster variation, to provide fitness-for-purpose signals for revealing general patterns and unique insights. Because this assessment relies on lens-conditioned inter-response dissimilarity, we propose a content-aware multi-agent system with two-stage instruction generation and adaptive anchors to improve scoring consistency. We validate QuAD through controlled experiments on synthetic data, including robustness and baseline comparisons, and a real-world social survey case study. The case study shows how QuAD quantitatively assesses whether a selected analysis axis is promising and also surfaces representative or unusual responses for human interpretation.
https://arxiv.org/abs/2610.23153
Large language model chatbots have been proposed as AI-interviewers for collecting qualitative interview data at scale, potentially bridging social science's longstanding divide between the breadth of surveys and the depth of qualitative interviews. This paper provides the first direct empirical comparison of data quality in AI-led and human-led interviews. In a randomized experiment (N = 41), university students were interviewed via synchronous text chat by either trained non-expert interviewers or a locally hosted AI system; we evaluate exposure, specificity, and relevance. Median interview duration was similar across conditions, but AI-interviewers asked more than twice as many questions per interview and elicited roughly 65 percent more respondent text per interview. Per-question responses were longer with human interviewers, though not after multiple-testing correction; only AI-condition participants skipped questions. Responses were almost uniformly on-topic in both conditions; for specificity we detect no difference, but the design cannot exclude one of up to three quarters of a point. These results were obtained with a small, locally hosted open-weight model (7B parameters), which addresses concerns about data security, GDPR compliance, and scientific reproducibility. Our findings support the viability of AI-interviewing for large-N qualitative data collection.
https://arxiv.org/abs/2610.23149
Large language model (LLM) agents are increasingly evaluated on long-horizon tasks, including autonomously running a business. Existing benchmarks for this setting are almost exclusively English-language, Western in retail context, and single-agent, with the agent observing the business directly. We study how these results transfer to a multi-agent Indic setting. We introduce KiranaBench, a simulated Indian general store in which four roles (manager, cashier, helper, and bookkeeper) are each played by a separate LLM agent. Interactions with customers and suppliers occur in English, Hindi, or Hinglish, and product demand is calibrated to India's national Household Consumption Expenditure Survey. Evaluating four open-weight LLMs, we find that all fall far short of a fixed-rule shopkeeper baseline: the best model earns only one-eighth of the baseline's profit, and two models finish below an unmanaged shop. Performance is also consistently lower for Hindi and Hinglish than for English supplier communication. KiranaBench offers evidence that current LLM agents are not yet reliable for autonomously operating small businesses in India, and provides a testbed for developing agents suited to settings that are long-horizon, collaborative, and multilingual.
https://arxiv.org/abs/2610.22980