#llm agents
Llm Agents: 14 AI articles covering llm agents news, analysis, and research
Articles
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverseโญ8
An audit of ToolUniverse finds 91 silent failures in agent-tool interaction, where successful tool calls return incomplete data, skewing to API and wrapper laye...
Recognition, Simulation, and Refusal: A Contamination-Awareโญ9
PsyAgentBench separates genuine psychological biases in LLM agents from contamination-driven imitation, testing Asch conformity, anchoring, and more across 41,9...
Your Agent Aced the Task. Will It Do It Again? | ALTK-Evolve andโญ10
ALTK-Evolve tackles the consistency problem in enterprise AI agents, explaining why they fail on repeat runs and how to make them dependable.
Subagents vs. Agent Skills: How to Execute Reusable Knowledgeโญ8
Subagent execution outperforms loading agent skills into context for long-horizon tasks. New arXiv research shows how organizing reusable knowledge as subagents...
DS-Lighting: Making Agent Harnesses Explicit for Data-Scienceโญ8
DS-Lighting introduces an explicit agent harness with reusable layers for data-science automation, improving reproducibility, comparability, and reliability acr...
Google AI Introduces EnvHarness: A Programmable Layer Turningโญ7
Google's EnvHarness adapts agent training environments dynamically, boosting performance by up to 9 points with 9.8% fewer steps.
Webwright: Why AI Web Agents Should Write Code, Not Clickโญ9
Web AI agents fail at multi-step tasks. New approach: write code instead of clicking, for durable, reusable automation.
Effective Project Management in the Age of AIโญ10
Discover how LLMs reshape project management, shifting engineers from coding to prompt orchestration, testing, and strategic oversight.
Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Tradingโญ9
Benchmarking LLM agents in algorithmic trading with Backtrader-Bench: tool-augmented models hit 90% accuracy, outpacing no-tool baselines by 17 points.
Using Agents as Tools: The Agent-as-a-Tool Pattern with OpenAIโญ10
Learn how to use the agent-as-a-tool pattern with OpenAI Agents SDK, enabling a manager agent to delegate tasks to specialist agents for complex workflows.
