Tag: LLM agents
Browse our exclusive articles!
Constant-Context Skill Learning for Efficient LLM Agents
Discover how constant-context skill learning boosts LLM agents' efficiency and privacy, achieving high success rates in multi-step workflows.
HiMAC: Hierarchical Learning for Long-Horizon LLM Agents
Discover HiMAC, a hierarchical learning framework boosting long-horizon planning and execution in LLM agents with improved efficiency and performance.
SkCC: Secure Portable Skill Compiler for LLM Agents
SkCC enables secure, portable skill compilation for LLM agents, improving performance, security, and cross-framework compatibility.
Reward Hacking Benchmark: Testing Exploits in LLM Agents
Discover how the Reward Hacking Benchmark evaluates exploit risks in RL-trained LLM agents using tools, revealing vulnerabilities and mitigation strategies...
OpenSeeker-v2: Advanced Search Agents with High-Difficulty Training
Discover how OpenSeeker-v2 uses informative, high-difficulty trajectories to train state-of-the-art search agents with simpler methods and top benchmark re...