Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/strands-agents/sdk-python
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Memory Aware Synapses: Learning what (not) to forget
- Task-Free Continual Learning
- Gradient based sample selection for online continual learning
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- On the Measure of Intelligence
- A continual learning survey: Defying forgetting in classification tasks
- PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
- MemGPT: Towards LLMs as Operating Systems
- Continual Lifelong Learning with Neural Networks: A Review
- Generative Agents: Interactive Simulacra of Human Behavior
- The Last Harness You'll Ever Build
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- A Comprehensive Survey of Continual Learning: Theory, Method and Application
- Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
- Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
- ReAct: Synergizing Reasoning and Acting in Language 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