HuggingFace
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation
Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files,...
HuggingFace
Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents f...
HuggingFace
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream sta...
HuggingFace
MARS: Multi-Specialist LLM Relay System for Competitive Programming
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existi...
arXiv
Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks
The Bayesian Ideal Observer (IO) establishes the theoretical upper bound on task performance for binary detection tas...
arXiv
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
Brain stroke, known for its high mortality and incidence rates, poses significant health risks and requires rapid int...
arXiv
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces...
arXiv
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
Clinicians read chain-of-thought (CoT) rationales as evidence of medical reasoning, but whether the visible chain pla...
arXiv
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize inter...
arXiv
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fix...
arXiv
Automatic Model Card Generation Using an LLM
Model cards are structured documents that summarize key information about machine learning models to improve transpar...