ScaffoldAgent introduces a utility-guided framework for dynamic outline optimization in open-ended deep research. It models outline evolution through Expansion, Contraction, and Revision operations, guided by a feedback mechanism that evaluates retrieval gain, structural coherence, and generation quality. Experiments show it improves long-form report generation and factual grounding compared to existing agents.
ModSync addresses capacity-induced failure in PINNs by preventing functional modularity and self-partitioning of overparameterized networks. It enhances cross-objective interaction through structural optimization that penalizes task-exclusive connections while preserving interaction-promoting pathways.
A formal psychometric analysis shows that apparent psychological profiles of large language models are primarily driven by response bias, not actual traits. This bias, which causes models to consistently favor one end of a scale, accounts for 81-90% of between-model variation, far exceeding human differences. The study concludes that these profiles are artifacts of instrument design and not true model properties, urging the development of assessments based on response orthogonality.
This paper proposes a framework for applying deep reinforcement learning to game AI, aiming to create more believable and human-like characters. It addresses current limitations in deploying machine learning agents in games and identifies key research challenges that could accelerate AI adoption in the video game industry.
This study analyzes and evaluates concept drift detection algorithms across various categories using synthetic and real-world streaming datasets. It examines drift characteristics and evaluates detector performance under abrupt and gradual drift scenarios to improve understanding of drift behavior and detector applicability.
A case study with a Nordic public knowledge institution demonstrates how editorial participation can re-align LLM interfaces with editorial standards. The paper introduces editorial alignment as a design practice in Participatory AI, where editorial values are translated into technical alignment objectives. This approach empowers editors with agency in LLM-mediated knowledge dissemination.
ELVA introduces a rule-based reinforcement learning framework to address grain blindness in multimodal retrieval. By using verifiable rewards and differentiating negative samples based on similarity, ELVA improves ranking precision and achieves a 13.1% gain on MRBench, a benchmark for multi-grain query scenarios.
The paper proposes SME-OFU, a novel algorithm for stochastic linear contextual bandits with bounded reward noise. It achieves a regret bound of O(log T) by leveraging set-membership estimation and optimism in the face of uncertainty. Simulations show SME-OFU outperforms a sub-Gaussian noise benchmark when reward noise is bounded.
A study across five Swiss cities compares TESSERA and AlphaEarth embeddings with traditional Sentinel data to upscale Local Climate Zone maps to 10-meter resolution using an attention-based U-Net. TESSERA consistently outperforms both Sentinel-1/2 and AlphaEarth, achieving IoU scores of 0.59–0.69 and 0.77–0.82. The results show embeddings reduce manual preprocessing and support scalable, reproducible LCZ mapping, though improved reference data is key for further accuracy gains.
The paper introduces optimal coarse correlated equilibria for continuous-time mean field games. It presents a linear programming formulation, proves existence, and develops a no-regret learning algorithm with explicit convergence rates, supported by numerical examples.
A new federated conformal risk control method addresses coverage failures in hospital-level predictions. On real brain tumor data from 20 institutions, pooled calibration fails 40% of sites, with one exceeding false-negative targets by 7.8 percentage points. The proposed shrinkage-based protocol uses empirical risk curves and a hyperparameter n0=19 to achieve 2.7/20 coverage violations at 2.0x prediction set stretch, while preserving marginal guarantees and ensuring no patient-level data leaves any site.
PASQA is a speech quality assessment model designed to evaluate pitch-accent correctness in synthetic Japanese speech. It uses a dataset with controlled accent errors and achieves high accuracy in ranking accent-error severity, outperforming conventional models and aligning better with human judgments.
Quantum vision models exhibit better generalization with more entanglement or quantum noise, phenomena unified by the effective dimension of the noise-shaped quantum feature kernel. This dimension acts as a regularization mechanism in overfitting regimes, with amplitude damping improving test accuracy by up to 13% along an inverted-U sweet spot.
This study analyzes and evaluates concept drift detection algorithms across multiple categories using synthetic and real-world streaming datasets. It examines drift characteristics and evaluates detector performance under abrupt and gradual drift scenarios to improve understanding of drift behavior and detector applicability.
QCPIKAN is the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations. It uses Chebyshev-polynomial KAN layers and parameterized quantum circuits to embed physical constraints into training, achieving exponential error convergence and reduced numerical dispersion. Validated on seepage scenarios in porous media, it outperforms existing quantum-classical neural networks in prediction accuracy, error control, and dynamic tracking.
We introduce Precision-Cache Hit Ratio (P-CHR) AUC and Calibration Retention Rate (CRR) to address the calibration gap in semantic caching. These metrics evaluate precision across cache utilization levels and measure how offline ranking quality persists in deployment. Our analysis shows the gap is driven by training objectives, not data scale, and post-hoc calibration only partially resolves it.
Multi-Agent Transactive Memory (MATM) enables population-level storage and retrieval of agent-generated trajectories. It allows producer agents to share procedural knowledge with consumer agents, improving task performance and reducing interaction steps in interactive environments like ALFWorld and WebArena without coordination or joint training.
A study measures tool-intent stabilization in Streaming RAG, defining when speculative tool queries converge to correct answers. On the CRAG benchmark, 73.9% of queries allow substantial latency hiding, with early stabilization observed in questions with verbatim retrievable evidence. Question type significantly predicts early versus late stabilization, informing when speculative triggers are effective.
PASQA is a speech quality assessment model designed to evaluate pitch-accent correctness in synthetic Japanese speech. It uses a dataset with controlled accent errors and incorporates self-supervised learning, mora-conditioned fusion, ranking loss, and accent-error localization to achieve high accuracy in detecting accent errors across speakers, outperforming conventional models in alignment with human judgments.
This paper introduces a four-layer technical architecture for token-oriented inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It reviews key technologies and industry status, analyzing their real-world application value in reducing token costs, enhancing service efficiency, and ensuring stable token supply.