From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
cs.LG, cs.CL
Submitted: 2026-10-08
Updated: 2026-10-08
Terminology
Sources
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- In-Place Test-Time Training
- SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
- When Does Continual Learning Require Learning
- LoRA: Low-Rank Adaptation of Large Language Models
- DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity
- Progressive Neural Networks
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
- Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks