Agent² RL-Bench: Evaluating LLM Agents in RL Post-Training
Discover how Agent² RL-Bench tests LLM agents' ability to engineer agentic reinforcement learning post-training with dynamic, interactive benchmarks.
EgoTSR: Advancing Ego-Centric Spatiotemporal AI Reasoning
Discover EgoTSR, a curriculum learning framework boosting ego-centric spatiotemporal reasoning for AI with 92.4% accuracy in long-horizon tasks.
Agent Mentor: Boost AI Agent Accuracy with Semantic Analysis
Enhance AI agent performance by refining natural language prompts using Agent Mentor's semantic trajectory analysis and corrective feedback pipeline.
How Intuitiveness Affects LLMs in Policy Evaluation
Explore how intuitiveness impacts large language models' counterfactual reasoning in policy evaluation, revealing key challenges and insights.
Resistance-Informed Framework for Realistic Client Simulation
Discover ResistClient, a framework enhancing psychological client simulators with resistance-informed motivation for realistic counselor training.