PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents
Research
Research News
New papers, breakthroughs and academic AI research
Chaining Skills to Hijack LLM Agents
Research
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
Research
UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
Research
Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
Research
Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
Research
PUMA: Learning a Mutation-Aware Vocabulary of Protein Units
Research
Context-Aware Error Mitigation Orchestration for Hybrid Quantum Reinforcement Learning on NISQ Systems
Research
LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing
Research
Multi-Party Backchannel Prediction: a Diagnosis, a Benchmark, and a Ceiling
Research
Low-Budget Active Learning through Entropic Optimal Transport
Research
FedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training
Research