Tag

LLM Agents

4 articles tagged with this topic.

Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning

A new arXiv paper proposes AgenticAI-Supervisor, a simulation environment that decouples environment creation from scalable execution for verifiable agentic RL.

Reinforcement Learning LLM Agents Simulation Environments Reward Shaping Agentic AI Training Methodology

Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

A synthesis of known failure modes in LLM-based agents, covering tool-use errors, planning breakdowns, and reasoning vulnerabilities that compound into systemic security risks.

LLM Agents Tool Invocation Planning Reasoning Prompt Injection Excessive Agency Auditability Insecure Tool Invocation arXiv

Information Gain-based Rollout Policy Optimization: Adaptive Tree-Structured Rollouts for Multi-Turn LLM Agents

IGRPO treats intermediate-state informativeness as the organizing principle of rollout collection, unifying tree-structured exploration with policy learning.

Reinforcement Learning LLM Agents Search-Augmented QA Agentic AI Training Methodology

PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents

PolyWorkBench evaluates LLM agents on long-horizon, multilingual tasks across five languages, revealing critical surface areas for prompt injection, insecure tool invocation, and excessive agency.

AI Security LLM Agents Benchmarking Prompt Injection Tool Invocation Excessive Agency

← All articles