ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting
arXiv:2603.14629v1 Announce Type: cross Abstract: ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question,…
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
arXiv:2603.12983v2 Announce Type: replace-cross Abstract: Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to…
Failure Detection in Chemical Processes Using Symbolic Machine Learning: A Case Study on Ethylene Oxidation
arXiv:2603.06767v2 Announce Type: replace-cross Abstract: Over the past decade, Artificial Intelligence has significantly advanced, mostly driven by large-scale neural approaches.…
Self Voice Conversion as an Attack against Neural Audio Watermarking
arXiv:2601.20432v2 Announce Type: replace-cross Abstract: Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual…
Sample-efficient generative molecular design using memory manipulation
Nature Machine Intelligence, Published online: 17 March 2026; doi:10.1038/s42256-026-01200-4 Guo et al. train a Mamba-based language model for molecule generation…
LLMs displaying less cognitive bias are not necessarily better decision makers
Nature Machine Intelligence, Published online: 17 March 2026; doi:10.1038/s42256-026-01208-w Large language models (LLMs) include not only social stereotypes but also…
Auditing Student-AI Collaboration: A Case Study of Online Graduate CS Students
arXiv:2601.08697v4 Announce Type: replace-cross Abstract: As generative AI becomes embedded in higher education, it increasingly shapes how students complete academic…
Maximum Entropy Exploration Without the Rollouts
arXiv:2603.12325v1 Announce Type: cross Abstract: Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective…
TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
arXiv:2603.12500v1 Announce Type: cross Abstract: We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction…
Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
arXiv:2603.12458v1 Announce Type: cross Abstract: While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual…