arXiv:2504.07384v2 Announce Type: replace Abstract: Phylogenetic trees are simple models of evolutionary processes. They describe conditionally independent divergent evolution from common ancestors. However, they often lack the flexibility to represent processes like introgressive hybridization, which leads to gene flow between taxa. Phylogenetic networks generalize trees but typically assume that ancestral taxa merge instantaneously to form […]
Secure Code Generation at Scale with Reflexion
arXiv:2511.03898v1 Announce Type: cross Abstract: Large language models (LLMs) are now widely used to draft and refactor code, but code that works is not necessarily secure. We evaluate secure code generation using the Instruct Prime, which eliminated compliance-required prompts and cue contamination, and evaluate five instruction-tuned code LLMs using a zero-shot baseline and a three-round […]
Habitat fragmentation promotes spatial scale separation under resource competition
arXiv:2511.04097v1 Announce Type: new Abstract: Habitat fragmentation, often driven by human activities, alters ecological landscapes by disrupting connectivity and reshaping species interactions. In such fragmented environments, habitats can be modeled as networks, where individuals disperse across interconnected patches. We consider an intraspecific competition model, where individuals compete for space while dispersing according to a nonlinear […]
I Detect What I Don’t Know: Incremental Anomaly Learning with Stochastic Weight Averaging-Gaussian for Oracle-Free Medical Imaging
arXiv:2511.03912v1 Announce Type: cross Abstract: Unknown anomaly detection in medical imaging remains a fundamental challenge due to the scarcity of labeled anomalies and the high cost of expert supervision. We introduce an unsupervised, oracle-free framework that incrementally expands a trusted set of normal samples without any anomaly labels. Starting from a small, verified seed of […]
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
arXiv:2510.17697v4 Announce Type: replace Abstract: Steering cooperative multi-agent reinforcement learning (MARL) towards desired outcomes is challenging, particularly when the global guidance from a human on the whole multi-agent system is impractical in a large-scale MARL. On the other hand, designing external mechanisms (e.g., intrinsic rewards and human feedback) to coordinate agents mostly relies on empirical […]
Collaborative Agents for Automated Program Repair in Ruby
arXiv:2511.03925v1 Announce Type: cross Abstract: Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development and the persistent challenges faced by its developers, has received little attention in APR research. […]
Testing the Testers: Human-Driven Quality Assessment of Voice AI Testing Platforms
arXiv:2511.04133v1 Announce Type: new Abstract: Voice AI agents are rapidly transitioning to production deployments, yet systematic methods for ensuring testing reliability remain underdeveloped. Organizations cannot objectively assess whether their testing approaches (internal tools or external platforms) actually work, creating a critical measurement gap as voice AI scales to billions of daily interactions. We present the […]
PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
arXiv:2511.03934v1 Announce Type: cross Abstract: We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting […]
Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Framework
arXiv:2511.03179v2 Announce Type: replace Abstract: The engineering design process often demands expertise from multiple domains, leading to complex collaborations and iterative refinements. Traditional methods can be resource-intensive and prone to inefficiencies. To address this, we formalize the engineering design process through a multi-agent AI framework that integrates structured design and review loops. The framework introduces […]
Direct Semantic Communication Between Large Language Models via Vector Translation
arXiv:2511.03945v1 Announce Type: cross Abstract: In multi-agent settings, such as debate, reflection, or tool-calling, large language models (LLMs) pass messages as plain tokens, discarding most latent semantics. This constrains information transfer and adds unnecessary computational overhead. We form a latent bridge via vector translations, which use learned mappings that enable direct semantic exchange between representation […]