Engineering
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
SkillZip is a graph compression framework for agent skill libraries that operates at the section level rather than treating each…
Engineering
Poor Man’s Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
Researchers introduced a methodology for efficiently simulating large-scale LLM-agent societies by substituting expensive individual language-model agents with low-parameter surrogate models…
Engineering
Self-Evolving Embodied Agents via Skill-Harness Evolution
The paper presents SHAPER, a framework that lets embodied AI agents improve their performance without updating any model weights. With…
Engineering
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Researchers introduced a test-time capability transfer method in which a stronger AI model constructs an inference-time harness that assists a…
Engineering
Sleeper Agents and How to Tame Them
Researchers at TNG Technology Consulting demonstrated how hidden malicious behavior can be embedded into large language models through reinforcement learning,…
Engineering
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
The paper introduces OpenART, an open-ended arena for scalable agent red teaming that evolves adversarial test environments and comprises over…
Engineering
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency
Researchers introduced NCP-Bench, a benchmark of 100 interactive narrative environments derived from film summaries, designed to evaluate whether language-model agents…
Engineering
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Researchers introduced Spark-to-Paper, a system that automates end-to-end research paper generation by implementing thirteen composable skills within an existing coding…
Engineering
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment
The paper introduces ToolHazard, a framework that automatically synthesizes adversarial environments to test the security of LLM-based agents that use…
Engineering
How Many of Your Agent’s Calls Actually Need a Frontier Model?
LangChain benchmarked NVIDIA’s open-source NeMo Switchyard model-routing library against its Deep Agents evaluation suite of 145 multi-step agentic tasks. Calls…
Engineering
TutorMoments: Do AI Tutors Know When to Help and When to Hold Back?
Researchers at the Allen Institute for AI introduced TutorMoments, a framework that pauses real one-on-one math tutoring transcripts at critical…
Engineering
Deploy local agents everywhere with LFM2.5-2.6B
Liquid AI has released LFM2.5-2.6B, a 2.6-billion-parameter model built for on-device agentic use cases. The model goes through a training…