arXiv:2603.21574v1 Announce Type: new Abstract: Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit assignment across agents difficult. Moreover, policy optimization in this setting is vulnerable to heavy-tailed and noisy rewards, which can […]
Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces
arXiv:2603.21692v1 Announce Type: new Abstract: As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing infrastructure requirement. Existing operational tooling addresses adjacent needs effectively: state checkpoint systems enable fault tolerance; observability platforms provide execution traces for debugging; telemetry standards ensure […]
The Presupposition Problem in Representation Genesis
arXiv:2603.21745v1 Announce Type: new Abstract: Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one whose states guide behavior in a content-sensitive way. Prior cognitive systems had already made this transition before we could examine it, and philosophy of […]
SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
arXiv:2603.22097v1 Announce Type: new Abstract: Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed […]
RedacBench: Can AI Erase Your Secrets?
arXiv:2603.20208v1 Announce Type: cross Abstract: Modern language models can readily extract sensitive information from unstructured text, making redaction — the selective removal of such information — critical for data security. However, existing benchmarks for redaction typically focus on predefined categories of data such as personally identifiable information (PII) or evaluate specific techniques like masking. To […]
Characterizing the ability of LLMs to recapitulate Americans’ distributional responses to public opinion polling questions across political issues
arXiv:2603.20229v1 Announce Type: cross Abstract: Traditional survey-based political issue polling is becoming less tractable due to increasing costs and risk of bias associated with growing non-response rates and declining coverage of key demographic groups. With researchers and pollsters seeking alternatives, Large Language Models have drawn attention for their potential to augment human population studies in […]
Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System
arXiv:2603.20250v1 Announce Type: cross Abstract: While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML […]
The AI Scientific Community: Agentic Virtual Lab Swarms
arXiv:2603.21344v1 Announce Type: new Abstract: In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling collective scientific exploration that mirrors real-world research communities. The framework leverages the inherent properties of […]
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
arXiv:2603.21383v1 Announce Type: new Abstract: Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce […]
Is the future of AI green? What can innovation diffusion models say about generative AI’s environmental impact?
arXiv:2603.21419v1 Announce Type: new Abstract: The rise of generative artificial intelligence (GAI) has led to alarming predictions about its environmental impact. However, these predictions often overlook the fact that the diffusion of innovation is accompanied by the evolution of products and the optimization of their performance, primarily for economic reasons. This can also reduce their […]
Beyond Correlation: Refutation-Validated Aspect-Based Sentiment Analysis for Explainable Energy Market Returns
arXiv:2603.21473v1 Announce Type: new Abstract: This paper proposes a refutation-validated framework for aspect-based sentiment analysis in financial markets, addressing the limitations of correlational studies that cannot distinguish genuine associations from spurious ones. Using X data for the energy sector, we test whether aspect-level sentiment signals show robust, refutation-validated relationships with equity returns. Our pipeline combines […]
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment
arXiv:2603.21558v1 Announce Type: new Abstract: Recursive self-improvement–where a model iteratively trains on its own outputs–promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations, errors in intermediate reasoning compound, leading to mode collapse and performance degradation. We propose Neuro-Symbolic Recursive Self-Alignment (NSRSA), which stabilizes iterative […]