AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning
arXiv:2510.06261v1 Announce Type: new Abstract: We present AlphaApollo, a self-evolving agentic reasoning system that aims to address two bottlenecks in…
EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
arXiv:2510.05942v2 Announce Type: replace-cross Abstract: We present EvalMORAAL, a transparent chain-of-thought (CoT) framework that uses two scoring methods (log-probabilities and…
Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
arXiv:2510.07022v1 Announce Type: cross Abstract: Machine unlearning is critical for enforcing data deletion rights like the “right to be forgotten.”…
AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
arXiv:2510.05379v2 Announce Type: replace-cross Abstract: Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power…
Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis
arXiv:2510.05106v1 Announce Type: new Abstract: The design of safety-critical agents based on large language models (LLMs) requires more than simple…
Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)
arXiv:2510.05016v2 Announce Type: replace-cross Abstract: While task-specific demonstrations show early success in applying large language models (LLMs) to automate some…
Segment-Factorized Full-Song Generation on Symbolic Piano Music
arXiv:2510.05881v1 Announce Type: cross Abstract: We propose the Segmented Full-Song Model (SFS) for symbolic full-song generation. The model accepts a…