Turn-level Multiscale Density Ratio Estimation for LLM Agents
cs.AI
Submitted: 2026-09-15
Updated: 2026-09-15
Comments: 15 pages, 9 figures, 3 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Qwen Technical Report
- FireAct: Toward Language Agent Fine-tuning
- Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
- Group-in-Group Policy Optimization for LLM Agent Training
- Adam: A Method for Stochastic Optimization
- SDPO: Segment-Level Direct Preference Optimization for Social Agents
- BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
- Chain of Hindsight Aligns Language Models with Feedback
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Direct Multi-Turn Preference Optimization for Language Agents
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
- Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning
- Qwen2 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- ScienceWorld: Is your Agent Smarter than a 5th Grader?
- RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
- How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection