arXiv:2604.01052v1 Announce Type: cross Abstract: “Vibe coding,” in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic’s Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly 512,000 lines of […]
BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction
arXiv:2604.00739v1 Announce Type: cross Abstract: Datasets used in immunotherapy response prediction are typically small in size, as well as diverse in cancer type, drug administered, and sequencer used. Models often drop in performance when tested on patient cohorts that are not included in the training process. Recent work has shown that transformer-based models along with […]
Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
arXiv:2509.25302v2 Announce Type: replace Abstract: The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective misalignment (just like Agent Smith in the movie The Matrix) has transitioned from a theoretical warning to a […]
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
arXiv:2603.26648v2 Announce Type: replace-cross Abstract: Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website […]
“Is This Really a Human Peer Supporter?”: Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
arXiv:2506.09354v2 Announce Type: replace-cross Abstract: Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access to psychosocial support. Peer support, grounded in lived experience, offers a valuable complement to professional care. However, variability in training, effectiveness, and definitions raises concerns about quality, consistency, and safety. Large Language Models (LLMs) present […]
Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
arXiv:2604.00733v1 Announce Type: cross Abstract: The memory wall remains the primary bottleneck for training large language models on consumer hardware. We introduce Spectral Compact Training (SCT), a method that replaces dense weight matrices with permanent truncated SVD factors W = U diag(s) V^T, where the full dense matrix is never materialized during training or inference. […]
CHIMERA-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design
arXiv:2603.13431v2 Announce Type: replace-cross Abstract: Computational antibody design has seen rapid methodological progress, with dozens of deep generative methods proposed in the past three years, yet the field lacks a standardized benchmark for fair comparison and model development. These methods are evaluated on different SAbDab snapshots, non-overlapping test sets, and incompatible metrics, and the literature […]
Closing the Confidence-Faithfulness Gap in Large Language Models
arXiv:2603.25052v2 Announce Type: replace-cross Abstract: Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic interpretability analysis of verbalized confidence, using linear probes and contrastive activation addition (CAA) steering to show […]
A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch
arXiv:2604.00730v1 Announce Type: cross Abstract: Context: Schools, training platforms, and technology firms increasingly need to assess programming proficiency at scale with transparent, reproducible methods that support personalized learning pathways. Objective: This study introduces a pedagogical framework for Scratch project assessment, aligned with the Common European Framework of Reference (CEFR), providing universal competency levels for students […]
Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
arXiv:2603.24324v2 Announce Type: replace-cross Abstract: Designing effective auxiliary rewards for cooperative multi-agent systems remains a challenging task. Misaligned incentives risk inducing suboptimal coordination, especially when sparse task feedback fails to provide sufficient grounding. This study introduces an automated reward design framework that leverages large language models to synthesize executable reward programs from environment instrumentation. The […]
Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment
arXiv:2604.01169v1 Announce Type: cross Abstract: A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are commonly modeled using simulators, which impose computational approximations. Meanwhile, experimental measurements more faithfully represent […]
GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization
arXiv:2604.00717v1 Announce Type: cross Abstract: Non-stationarity arises from concurrent policy updates and leads to persistent environmental fluctuations. Existing approaches like Centralized Training with Decentralized Execution (CTDE) and sequential update schemes mitigate this issue. However, since the perception of the policies of other agents remains dependent on sampling environmental interaction data, the agent essentially operates in […]