EvoBelief: Falsifiable World Models for Self-Improving LLM Agents
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
- Dream to Control: Learning Behaviors by Latent Imagination
- PABU: Progress-Aware Belief Update for Efficient LLM Agents
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
- LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
- Towards a Belief-Based World Model for LLM Agents
- Meta-Harness: End-to-End Optimization of Model Harnesses
- WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
- Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
- Belief Memory: Agent Memory Under Partial Observability
- Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
- ProPlay: Procedural World Models for Self-Evolving LLM Agents
- Agentic Forecasting with Structured Linguistic Beliefs
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- A Self-Improving Coding Agent
- Hypothesis-Driven Skill Optimization for LLM Agents
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
- Ask the World Before Acting: Environment Probing for Calibrated Agent World Models
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
- Agents' Last Exam
- 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