arXiv:2605.04361v1 Announce Type: new Abstract: The prevailing assumption in agent orchestration is that more context is better. We test this on multi-agent software design across 10 tasks, 7 context-injection conditions, and over 2,700 runs, and find a crossover effect: the same artifact type improves design exploration on some tasks (up to 20$times$ tradeoff coverage) and […]
Relational In-Context Learning via Synthetic Pre-training with Structural Prior
arXiv:2603.03805v3 Announce Type: replace-cross Abstract: Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, We introduce $textbfRDB-PFN$, the first relational foundation […]
CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement
arXiv:2605.04677v1 Announce Type: cross Abstract: We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS), automated code refinement, and language-specific evaluation pipelines for Java and Salesforce Apex. The system uses Java Flight Recorder (JFR) profiles […]
Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks
arXiv:2605.04443v1 Announce Type: new Abstract: Deep convolutional neural networks (DCNNs) have rivaled humans on many visual tasks, yet they remain vulnerable to near-imperceptible perturbations generated by adversarial attacks. Recent work shows that aligning DCNN representations with human visual cortex activity improves adversarial robustness, but the mechanisms driving this advantage are unclear. One hypothesis suggests that […]
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
arXiv:2605.04702v1 Announce Type: cross Abstract: Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose textitFaithfulFaces, a pose-faithful facial identity preservation learning framework to […]
Code Broker: A Multi-Agent System for Automated Code Quality Assessment
arXiv:2604.23088v2 Announce Type: replace-cross Abstract: We present Code Broker, a multi agent system built on Google s Agent Development Kit ADK that analyses Python source code from individual files, local directory trees, or remote GitHub repositories and generates structured, actionable quality assessment reports. The system realises a hierarchical five agent architecture in which a root […]
AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education
arXiv:2605.04740v1 Announce Type: cross Abstract: Effective peer feedback is essential for developing critical reflection in higher education, yet its impact is often limited by the inconsistent quality of student-generated comments. This paper presents the implementation and deployment of AICoFe (AI-based Collaborative Feedback), a system designed to bridge this gap through a human-centered AI approach. We […]
Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone
arXiv:2605.04454v1 Announce Type: new Abstract: Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction following, or pairwise preference, and these scores are often used to support claims about deployed alignment. This paper argues that deployment-relevant alignment cannot be inferred from model-level […]
How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier Models
arXiv:2605.04488v1 Announce Type: new Abstract: We evaluate whether enabling provider-exposed reasoning mode changes moral judgments within the same model checkpoint. Across 100 moral-judgment scenarios and five frontier reasoning-trained LLMs (Claude Sonnet 4.6, GPT 5.5, Gemini 3 Flash, DeepSeek V3.1, and Qwen3.5 397B), aggregate binary-verdict agreement remains high and statistically indistinguishable between instant and thinking modes […]
Federated Learning for Early Prediction of EV Charging Demand
arXiv:2605.04993v1 Announce Type: cross Abstract: Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimization. In this work, we study the problem of early prediction of charging demand, where the total energy of a session is estimated using only information available at plug-in time and during […]
Algorithmic bottlenecks in evolution: Genetic code, symbolic language, and the Great Filter hypothesis
arXiv:2605.04498v1 Announce Type: new Abstract: The Great Filter hypothesis proposes that the emergence of technological societies capable of interstellar travel depends on a small number of exceptionally hard and highly improbable steps. Traditional versions of this hypothesis enumerate such “hard steps” along the trajectory from inanimate matter to complex technological societies, but diverge in their […]
The Impossibility Triangle of Long-Context Modeling
arXiv:2605.05066v1 Announce Type: cross Abstract: We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent of sequence length (Efficiency), (ii) state size independent of sequence length (Compactness), and (iii) the ability to recall a number of historical facts proportional to sequence length (Recall). We formalize this […]