arXiv subjects

Artificial intelligence

Search indexed arXiv papers on artificial intelligence and machine learning, including cs.AI metadata. Follow the original manuscripts for methods, experiments and version history.

Follow this topic with RSS

At least 469 records · Page 26Linked to original sources

arXiv2026

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

AI-assisted coding increasingly translates informal user intent into executable software, yet coding requests often contain ambiguities that recur in user-specific ways across tasks and sessions. Existing disambiguation methods typically address each ambiguous request in isolation within the current coding session, often through eliciting additional clarification. However, whether resolved session history from the same user can serve as memory for resolving recurring personalized ambiguity in a newly opened session remains underexplored. We formulate personalized ambiguity adaptation as a new task: given a user's previously resolved coding sessions and a new ambiguous request, an assistant should identify the recurring ambiguity pattern, produce the intended executable solution, and minimize clarification. To benchmark this task, we introduce CAPA, which characterizes personalized coding ambiguity through six mechanisms and injects these mechanisms into unambiguous executable tasks using a controlled three-stage generation pipeline. CAPA contains 600 coding sessions across 60 balanced user--ambiguity cells, including 300 held-out evaluation sessions. We evaluate 12 recent LLMs under no-history and same-user-history conditions using executable success, first-turn success, and turns-to-completion. Our analyses examine task difficulty, user identity, and memory-based history use, and we further propose same-user history gating as a lightweight inference-time method. CAPA provides a foundation for developing long-term coding assistants that better align generated code with user intent while reducing repeated clarification.

cs.AI↗

arXiv2026

Understanding Context Sampling in TabPFN on Small Tabular Datasets

TabPFN performs classification through in-context learning: it conditions on a set of labeled training rows (the context, or prototypes) and predicts test labels without gradient updates. On small tabular datasets, practitioners must still choose the context size and which rows constitute the context. We study how these choices affect prediction stability, accuracy, and selection cost using repeated context sampling on 15 OpenML datasets. Specifically, we investigate (i) whether larger contexts reduce prediction variability across random draws, (ii) whether accuracy depends on preserving the training distribution or on feature-space coverage, and (iii) whether expensive selection methods such as K-Means and farthest-point sampling provide benefits over uniform random sampling. We find that larger contexts are both more accurate and substantially more stable, with AUC coefficient of variation decreasing from roughly 6 to 18% at k=16 to 1 to 4% at larger context sizes on datasets with room for improvement. Although accuracy correlates with distribution representativeness in random contexts, controlled experiments show that matching feature means alone can reduce accuracy by up to 0.5 AUC because it reduces context diversity. Mixed-effects analysis identifies diversity and coverage, rather than feature-mean matching, as the stronger predictor of accuracy (diversity beta=+0.23, p=3x10^-12; feature-mean shift beta=-0.01, p=0.71). K-Means and farthest-point sampling achieve similar accuracy to random selection while requiring two to three orders of magnitude more selection cost. These results show that random sampling succeeds because it provides feature-space coverage in expectation, not because it reproduces the underlying data distribution.

cs.LG↗

arXiv2026

ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories

This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework implements a versioned, safety-governed evaluation contract that checks whether a recommendation is supported by the available evidence, permitted under the stated authority and procedure, and acceptable under the plant-specific consequence checks encoded in the selected evaluation profile. In this report, \emph{safety-governed} means that eligibility is determined through explicit, non-compensatory checks derived from a versioned plant profile; it does not mean that the evaluator, model, or plant has been safety-certified. Release 0.1.0 is a public reference implementation for technical and research evaluation, not an authorisation for physical execution.

cs.AI↗

arXiv2026

Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution

Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-world code snippets to fail at execution. This paper presents PLLM+, a hybrid dependency-repair pipeline evaluated on the HG2.9K benchmark of 2,891 dependency-failing snippets. PLLM+ prioritizes inexpensive deterministic steps before invoking LLM-based repair: static AST-based interpreter inference, replay of historically successful dependency configurations from the competition-provided solutions database, and live PyPI validation of candidate package versions. When these steps do not resolve a case, the system falls back to a structured LLM-based repair loop with typed error classification and Proposer/Critic agents. On HG2.9K, PLLM+ solves 1,500 out of 2,891 snippets, compared with 1,169 solved by the PLLM baseline. It also reduces average runtime from 368.7 to 71.8 seconds per snippet. Most successful fixes come from replaying known configurations: 1,495 of the 1,500 successful fixes are produced by the solutions database, while the LLM fallback accounts for 5 additional fixes. These results suggest that, in this benchmark setting, deterministic reuse of previously validated dependency configurations is a simple and effective strategy, with LLM-based repair serving as a secondary fallback for cases not covered by prior solutions.

cs.AI↗

arXiv2026

DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation

Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process. We introduce DocAnnot, a framework that significantly accelerates KIE dataset generation. DocAnnot leverages a Large Vision Language Model (LVLM) for label value extraction, OCR for text/bounding box detection, and a novel Spatially Informed Contextual Matching (SICM) algorithm. SICM improves label-value association by combining spatial relationships and proximity analysis with textual matching. We evaluate our framework on the CORD and SROIE benchmarks, demonstrating its ability to auto-generate annotations with F1-scores of 0.679 and 0.846, respectively. Furthermore, we investigate the effectiveness of using auto-annotated data for fine-tuning downstream KIE models. While human-annotated data remains superior, models trained exclusively on DocAnnot's outputs attain respectable performance (e.g., LayoutLMv3 achieving an F1-score of 0.6765 on CORD). These results show that while our framework significantly reduces reliance on manual effort, it does not yet fully eliminate the need for human intervention. However, by automating the process to a point where reviewers can efficiently refine outputs, our system enables near-perfect annotations with much greater efficiency than manual annotation from scratch. This approach offers substantial time and cost savings, making it valuable for resource-constrained settings and rapid model prototyping.

cs.IR↗

arXiv2026

When Shortest Isn't Safest: A Design Science Approach to Senior-Friendly Pedestrian Routing

Older adults' independent mobility enables out-of-home participation, well-being and health, yet pedestrian navigation systems still optimize primarily for distance or time, often overlooking barriers, safety thresholds, and supportive infrastructure that shape late-life walking decisions. We present a senior-friendly pedestrian routing artefact developed through echeloned Design Science Re-search, translating lived mobility constraints into prescriptive design knowledge. Based on 11 semi-structured interviews, we derive initial Design Requirements (DRs) and Design Principles (DPs) for barrier-aware, amenity-sensitive routing and execution-relevant explanations. We instantiate these in an OpenStreetMap pedestrian network enriched with amenities (benches, toilets, and shelters) and height data, and implemented an A*-based routing engine with configurable costs and explanation payloads. In a field-based walking study, 14 older adults com-pared artefact-generated routes with baselines and provided ratings and qualitative feedback; the senior-friendly route was preferred overall. Thematic analysis further showed that infrastructure maintenance, seasonal conditions, traffic exposure, and social context shape route acceptance. We synthesize these insights into refined DRs and DPs emphasizing context-aware hazard modeling, multi-route transparency, landmark-grounded explanations, social-context sensitivity, and stage-appropriate information. Our contributions provide actionable guidance for practitioners developing senior-friendly pedestrian navigation systems.

cs.AI↗

arXiv2026

Thermodynamic Limits of Physical Intelligence

Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption. To connect intelligence to physical efficiency, we propose two complementary bits-per-joule metrics under explicit accounting conventions: (1) Thermodynamic Epiplexity per Joule, new bits of structure about a specified environment-instance variable encoded in an agent's state per unit energy, and (2) Empowerment per Joule, sensorimotor channel capacity per expected energetic cost over a fixed horizon. These give two axes of physical intelligence, recognition versus control, but the resulting numbers are benchmark-relative rather than universal. Drawing on stochastic thermodynamics, we formulate a Landauer-scale closed-cycle benchmark for epiplexity acquisition by combining a thermodynamic-learning inequality with data processing, and clarify why boundary closure is required; conversely, a decoupling construction shows that without such assumptions information gain and in-boundary dissipation need not be tightly linked. For empirical settings where the latent structure variable is unavailable, we recommend compute-bounded MDL epiplexity / compression-gain surrogates. Finally, we propose a unified efficiency framework with a minimal checklist of conventions for relative bits-per-joule comparisons, and give a compact language-model reporting example.

cs.LG↗

arXiv2012

The Guppy Effect as Interference

People use conjunctions and disjunctions of concepts in ways that violate the rules of classical logic, such as the law of compositionality. Specifically, they overextend conjunctions of concepts, a phenomenon referred to as the Guppy Effect. We build on previous efforts to develop a quantum model that explains the Guppy Effect in terms of interference. Using a well-studied data set with 16 exemplars that exhibit the Guppy Effect, we developed a 17-dimensional complex Hilbert space H that models the data and demonstrates the relationship between overextension and interference. We view the interference effect as, not a logical fallacy on the conjunction, but a signal that out of the two constituent concepts, a new concept has emerged.

cs.AI↗

arXiv2026

StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting

Most existing Face Forgery Detection (FFD) models assume access to raw face images. In practice, under a client-server framework, private facial data may be intercepted during transmission or leaked by untrusted servers. Previous privacy protection approaches, such as anonymization, encryption, or distortion, partly mitigate leakage but often introduce severe semantic distortion, making images appear obviously protected. This alerts attackers, provoking more aggressive strategies and turning the process into a cat-and-mouse game. Moreover, these methods heavily manipulate image contents, introducing degradation or artifacts that may confuse FFD models, which rely on extremely subtle forgery traces. Inspired by advances in image steganography, which enable high-fidelity hiding and recovery, we propose a Stega}nography-based Face Forgery Detection framework (StegaFFD) to protect privacy without raising suspicion. StegaFFD hides facial images within natural cover images and directly conducts forgery detection in the steganographic domain. However, the hidden forgery-specific features are extremely subtle and interfered with by cover semantics, posing significant challenges. To address this, we propose Low-Frequency-Aware Decomposition (LFAD) and Spatial-Frequency Differential Attention (SFDA), which suppress interference from low-frequency cover semantics and enhance hidden facial feature perception. Furthermore, we introduce Steganographic Domain Alignment (SDA) to align the representations of hidden faces with those of their raw counterparts, enhancing the model's ability to perceive subtle facial cues in the steganographic domain. Extensive experiments on seven FFD datasets demonstrate that StegaFFD achieves strong imperceptibility, avoids raising attackers' suspicion, and better preserves FFD accuracy compared to existing facial privacy protection methods.

cs.CV↗

arXiv2026

Towards Understanding the Cognitive Habits of Large Reasoning Models

Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that certain CoT patterns -- e.g., ``Wait, did I miss anything?'' -- consistently emerge across tasks, we explore whether LRMs exhibit human-like cognitive habits. Building on Habits of Mind, a well-established framework of cognitive habits associated with successful human problem-solving, we introduce CogTest, a principled benchmark designed to evaluate LRMs' cognitive habits. CogTest includes 16 cognitive habits, each instantiated with 25 diverse tasks, and employs an evidence-first extraction method to ensure reliable habit identification. With CogTest, we conduct a comprehensive evaluation of 16 widely used LLMs (13 LRMs and 3 non-reasoning ones). Our findings reveal that LRMs, unlike conventional LLMs, not only exhibit human-like habits but also adaptively deploy them according to different tasks. Finer-grained analyses further uncover patterns of similarity and difference in LRMs' cognitive habit profiles, particularly certain inter-family similarity (e.g., Qwen-3 models and DeepSeek-R1). Extending the study to safety-related tasks, we observe that certain habits, such as Taking Responsible Risks, are strongly associated with the generation of harmful responses. These findings suggest that studying persistent behavioral patterns in LRMs' CoTs is a valuable step toward deeper understanding of LLM misbehavior. The code is available at: https://github.com/jianshuod/CogTest.

cs.CL↗

arXiv2021

An effective hybrid search algorithm for the multiple traveling repairman problem with profits

As an extension of the traveling repairman problem with profits, the multiple traveling repairman problem with profits consists of multiple repairmen who visit a subset of all customers to maximize the revenues collected through the visited customers. To solve this challenging problem, an effective hybrid search algorithm based on the memetic algorithm framework is proposed. It integrates two distinguished features: a dedicated arc-based crossover to generate high-quality offspring solutions and a fast evaluation technique to reduce the complexity of exploring the classical neighborhoods. We show the competitiveness of the algorithm on 470 benchmark instances compared to the leading reference algorithms and report new best records for 137 instances as well as equal best results for other 330 instances. We investigate the importance of the key search components for the algorithm.

cs.NE↗

arXiv2026

Humanity's Last Exam

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

cs.LG↗

arXiv2026

Balancing Centralized Learning and Distributed Self-Organization: A Hybrid Model for Embodied Morphogenesis

Background: both embodied intelligence and developmental morphogenesis depend on a division of labour between centralized guidance and distributed material dynamics, but the amount of top-down control needed to steer self-organization remains unclear. Methods: we coupled a compact full-resolution convolutional controller to a differentiable Gray-Scott reaction-diffusion (RD) substrate. The controller observes two fields, U and V, and applies smooth gain-scheduled modulations of the feed and kill parameters (Delta F and Delta K). We compared pure RD, neural network (NN)-dominant and hybrid regimes and evaluated spectral selectivity, convergence and control cost. Results: the hybrid regime achieved 100% strict convergence at approximately 165 steps, whereas pure RD and the NN-dominant baseline did not converge within the same horizon. It matched the substrate's spectral selectivity while using approximately 15 times less L1 effort and over 200 times less L2 power than the NN-dominant controller. Moderate amplitudes (A approximately 0.03-0.045) formed a Goldilocks zone with 100% quasi-convergence in 94-96 steps. Conclusions: effective control is best framed as seed then cede: brief, smooth parameter-level nudges place the system in a favourable basin of attraction, after which reaction-diffusion dynamics complete and stabilize the pattern. This provides a quantitative model of morphological computation for controlled self-organization.

cs.AI↗

arXiv2026

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently require repeated domain-specific fine-tuning, which is a costly cycle that becomes impractical when labels are scarce or privacy constraints limit data sharing. We propose OPERA (Offline Policy-guided Expert Routing and Adaptation), a multi-agent ensemble framework that addresses this deployment bottleneck by treating expert weight assignment as an offline policy learning problem: a routing policy is learned from a small validation set without gradient updates to any expert agent, then deployed with test-time adaptation to handle distribution shift. OPERA coordinates heterogeneous specialist agents through complementary mechanisms. The expert profiling module learns selection policies offline, enabling informed allocation of expertise. Each agent undergoes confidence calibration through temperature adjustment, ensuring more reliable probabilistic outputs. OPERA also incorporates distribution aware adaptation, where class weights are dynamically adjusted at the batch level using statistics derived from unlabeled test data. Instance level routing assigns each sample to the most suitable expert by leveraging inter model agreement and predictive entropy. We evaluate OPERA on 9 datasets covering fundus photography, chest X-ray, CT, MRI, and multimodal diagnostic benchmarks, comparing against 30+ baselines across classification, segmentation, and multimodal settings. OPERA consistently improves performance and calibration quality, demonstrating that offline policy-guided expert agents coordination is a practical path to deployable biomedical AI without retraining. Code is on \href{https://github.com/HUANGLIZI/OPERA}{GitHub}.

cs.CV↗

arXiv2026

HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising

Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL policies) but face two critical limitations: lack of online adaptability to non-stationary auction markets, and reliance on costly manual tuning of hyperparameters such as bid bounds and budget pacing constraints. We propose HOBA (Hierarchical On-policy Bidding Agents), a hierarchical reinforcement learning framework that decouples strategic reasoning, model selection, and bid execution across three time scales. At the high level, a large language model infers hyperparameters from contextual signals through a Think-Act-Observe-Reflect loop with historical experience retrieval. At the mid level, a SARSA agent dynamically selects among expert models, incorporating causal adjustment to eliminate selection bias. At the low level, a dynamic expert pool (PID, MPC, IQL, Decision Transformer) executes bids under high-level constraints. This design confines online learning to discrete expert selection rather than continuous bid optimization, significantly reducing exploration risk while maintaining adaptability. Experiments on the AuctionNet benchmark and a large-scale A/B test demonstrate consistent improvements over state-of-the-art baselines. In a large-scale online deployment, HOBA delivered substantial business value, achieving a +3.6\% increase in target cost, proving the effectiveness of our hierarchical multi-agent bidding paradigm.

cs.AI↗

arXiv2026

Real-time Spatial Retrieval Augmented Generation for Urban Environments

The proliferation of Generative Artificial Ingelligence (AI), especially Large Language Models, presents transformative opportunities for urban applications through Urban Foundation Models. However, base models face limitations, as they only contain the knowledge available at the time of training, and updating them is both time-consuming and costly. Retrieval Augmented Generation (RAG) has emerged in the literature as the preferred approach for injecting contextual information into Foundation Models. It prevails over techniques such as fine-tuning, which are less effective in dynamic, real-time scenarios like those found in urban environments. However, traditional RAG architectures, based on semantic databases, knowledge graphs, structured data, or AI-powered web searches, do not fully meet the demands of urban contexts. Urban environments are complex systems characterized by large volumes of interconnected data, frequent updates, real-time processing requirements, security needs, and strong links to the physical world. This work proposes a real-time spatial RAG architecture that defines the necessary components for the effective integration of generative AI into cities, leveraging temporal and spatial filtering capabilities through linked data. The proposed architecture is implemented using FIWARE, an ecosystem of software components to develop smart city solutions and digital twins. The design and implementation are demonstrated through the use case of a tourism assistant in the city of Madrid. The use case serves to validate the correct integration of Foundation Models through the proposed RAG architecture.

cs.AI↗

arXiv2026

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions

We propose Concept Tokens, a lightweight method that adds a new special token to a pretrained LLM and learns only its embedding from multiple natural language definitions of a target concept, where occurrences of the concept are replaced by the new token. The LLM is kept frozen and the embedding is optimized with the standard language-modeling objective. We evaluate Concept Tokens in three settings. First, we study hallucinations in closed-book question answering on HotpotQA and find a directional effect: negating the hallucination token reduces hallucinated answers mainly by increasing abstentions, whereas asserting it increases hallucinations and lowers precision. Second, we induce recasting, a pedagogical feedback strategy for second language teaching, and observe the same directional effect. Moreover, compared to providing the full definitional corpus in-context, concept tokens better preserve compliance with other instructions (e.g., asking follow-up questions). Finally, we include a qualitative study with the Eiffel Tower and a fictional "Austral Tower" to illustrate what information the learned embeddings capture and where their limitations emerge. Overall, Concept Tokens provide a compact control signal learned from definitions that can steer behavior in frozen LLMs.

cs.CL↗

arXiv2026

Position: Evaluation Scores Are Perishable Knowledge Claims

Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with three properties: formality (human evaluation provides stronger evidence than an automated metric), scope (a benchmark result applies to the tested distribution, not universally), and validity windows (benchmark results expire as contamination accumulates and distributions shift). Several converging research traditions (chain-of-thought analysis, possibilistic logic, and algebraic theory) establish weakest-link aggregation as the conservative endpoint of a parameterized operator family controlled by a single pessimism parameter. Drawing on those traditions, and on concrete lessons from building an evaluation harness for agentic AI, we propose that evaluation results carry explicit metadata (formality tier, scope declaration, and expiration date) to make their epistemic status transparent. We illustrate the cost of mean aggregation on the public HELM leaderboard: across 54 frontier models on ten scenarios, the top-five models ranked by mean score and by weakest-link are completely disjoint.

cs.AI↗