Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/THUDM/VisualAgentBench
Sources
- Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemGPT: Towards LLMs as Operating Systems
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
- AdaMEM: Test-Time Adaptive Memory for Language Agents
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
- SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks