1 day ago
Retro gaming is being overrun with AI
Retro video games are everywhere lately – especially in places where they aren't supposed to be. Halo in a web browser, Wind Waker on the iPhone, Super Smash Bros. in mixed reality. Over the…
SUPER INTELLIGENCE BREAK
INTELLIGENCE LIBRARY
The Signal.
A focused stream of intelligence from the sources you trust.
182 resultsSorted by latest
2 days ago
RoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation
arXiv:2610.30429v1 Announce Type: new Abstract: Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable dynamic orchestration, trajectory-level rewards they…
2 days ago
Breaking the high-degree barrier in Lehmer's problem with a human-AI discovery loop
arXiv:2610.30277v1 Announce Type: new Abstract: While artificial intelligence has made rapid progress in mathematical reasoning, many open problems depend on structure that is revealed only through large-scale computational exploration and analytical synthesis. One such…
2 days ago
CollabFlow: Recursive Self-Improvement of Agent Collaboration
arXiv:2609.38662v3 Announce Type: replace-cross Abstract: Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how they collaborate across…
2 days ago
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
arXiv:2605.14089v2 Announce Type: replace Abstract: In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including…
2 days ago
Automated screening of privacy risks in medical AI
arXiv:2610.30229v1 Announce Type: new Abstract: Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them. However, a model can reveal whether a patient's records…
2 days ago
AI Mindmeld: A Latent Interconnect Protocol
arXiv:2610.30215v1 Announce Type: new Abstract: LLMs can act as scientific agents using tools to consult specialists and run experiments. Yet specialist information must enter their context, generally as text, images, audio or video: a…
2 days ago
Interface-Induced Trajectory Censoring
arXiv:2609.03966v3 Announce Type: replace-cross Abstract: Tool-use evaluations typically measure calls through a serving stack, which can report zero calls even when model outputs contain call-shaped payloads. We study interface-induced trajectory censoring: a mismatch between…
2 days ago
Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity
arXiv:2610.31436v1 Announce Type: cross Abstract: Automated agentic-system design is typically evaluated on static task suites with immediate scalar rewards. Deployed systems face persistent shift, delayed dependent feedback, correlated component failures, and costly architecture changes.…
2 days ago
SIM-UT: A User Simulation based Evaluation Framework for Medical Triage Chatbots
arXiv:2610.30412v1 Announce Type: new Abstract: LLM-based chat agents are increasingly used for complex, multi-turn, multilingual medical triage in low- and middle-income countries (LMICs), yet evaluation methods focus on single-turn, English-only benchmarks that primarily test…
2 days ago
TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents
arXiv:2610.30161v1 Announce Type: new Abstract: Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but…
2 days ago
Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks
arXiv:2610.26589v2 Announce Type: replace-cross Abstract: Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to the victim model. Yet each additional call gives the deployed system another opportunity…