llm agents
LLM agents refer to agents powered by large language models (LLMs) that can perform a variety of tasks such as understanding and generating text. These agents have become pivotal in conversational AI, automated customer support systems, and content creation.
- Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations
- Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
- From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
- How to Train Your LLM Web Agent: A Statistical Diagnosis
- MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
- Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
- SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data
- TAI3: Testing Agent Integrity in Interpreting User Intent
- VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
- VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
- WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents