Residual Stream Analysis of Overfitting And Structural Disruptions
arXiv:2603.13318v1 Announce Type: cross Abstract: Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge:…
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
arXiv:2603.15262v1 Announce Type: new Abstract: Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs)…
Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
arXiv:2603.15054v1 Announce Type: new Abstract: Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet,…
Why AI systems don’t learn and what to do about it: Lessons on autonomous learning from cognitive science
arXiv:2603.15381v1 Announce Type: new Abstract: We critically examine the limitations of current AI models in achieving autonomous learning and propose…
s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
arXiv:2603.14628v1 Announce Type: cross Abstract: Neurosymbolic approaches leveraging Large Language Models (LLMs) with formal methods have recently achieved strong results…
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…