State of LLM Agents

Top papers

• LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study(8.0)
• MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models(7.0)
• From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents(7.0)
• MemArchitect: A Policy Driven Memory Governance Layer(7.0)
• Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety(7.0)
• Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents(7.0)
• Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments(7.0)
• One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States(7.0)
• ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMs(7.0)
• EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning(7.0)
• AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling(7.0)
• BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents(7.0)
• Act While Thinking: Accelerating LLM Agents via Pattern-Aware Speculative Tool Execution(5.0)
• Security awareness in LLM agents: the NDAI zone case(4.0)
• Understanding the Challenges in Iterative Generative Optimization with LLMs(3.0)