Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance

TL;DR

The paper presents Agent K, the first LLM-based agent that integrates Kolb's experiential learning cycle with Vygotsky's ZPD to perform fully autonomous, end-to-end Kaggle data science tasks. By separating extrinsic environment interaction from intrinsic reflection and abstraction, Agent K progresses from scaffolded learning to open-ended generalization, achieving human-competitive Elo-MMR and medal-level results across tabular, CV, NLP, and multimodal challenges. The approach introduces modular intrinsic/extrinsic functions, scaffold-derived chain-of-thoughts, and a suite of tools (feature engineering, blending, class-balancing) that enable robust, cognitively grounded learning. This work demonstrates a significant advance toward generalist AI by showing that human-like learning cycles can underpin scalable, autonomous problem solving in open-ended real-world domains.

Abstract

Human expertise emerges through iterative cycles of interaction, reflection, and internal model updating, which are central to cognitive theories such as Kolb's experiential learning and Vygotsky's zone of proximal development. In contrast, current AI systems, particularly LLM agents, rely on static pre-training or rigid workflows, lacking mechanisms for continual adaptation. Recent studies identified early cognitive traits in LLM agents (reflection, revision, and self-correction) suggesting foundational elements of human-like experiential learning. Thus the key question: Can we design LLM agents capable of structured, cognitively grounded learning similar to human processes? In response, we propose a computational framework of Kolb's learning cycle with Vygotsky's ZPD for autonomous agents. Our architecture separates extrinsic (environment interaction) and intrinsic (internal reflection/abstraction) functions, enabling cognitively grounded scaffolded learning, where the agent initially learns within structured environments, followed by open-ended generalisation. This approach empowers agents to master complex tasks ; domains that traditional fine-tuning or simple reflective methods could not tackle effectively. Its potential is powerfully demonstrated via direct comparison with humans in real-world Kaggle data science competitions. Learning fully automated data science code generation across 81 tasks, our system, Agent K, demonstrated the ability to perform the entire workflow autonomously, achieving an Elo-MMR score of 1694, beyond median score of the Kaggle Masters (the top 2% among 200,000 users) of our study. With 9 gold, 8 silver, and 12 bronze medals level performance - including 4 gold and 4 silver on prize-awarding competitions - Agent K is the 1st AI system to successfully integrate Kolb- and Vygotsky-inspired human cognitive learning, marking a major step toward generalist AI.

Figures (13)

• Figure 1: Our computational formalisation of Kolb's experiential learning theory.
• Figure 2: From Scaffolded Experiential Learning to Autonomous Generalisation. The top part of the figure shows how an autonomous agent progresses from scaffolded learning tasks within its Zone of Proximal Development (ZPD) to open-ended problem solving. In the scaffolded environment (on top left), the agent generates solutions though structured tasks gated by success and supported by feedback. As the agent masters scaffolded tasks, it internalises strategies into Scaffold-CoTs -- realised through LLM summarisation in our setup. In the open-ended environment (on the top right), the scaffold is removed, and the abstracted knowledge supports self-directed adaptation to increase the likelihood of success. Learning in both regimes follows our computational model of Kolb’s experiential learning cycle: concrete interaction with the environment (extrinsic functions), reflective observation and internal strategy formation (intrinsic functions), and active experimentation based on revised hypotheses. The two bottom graphs illustrate this experiential learning process via prompt-based intrinsic and extrinsic functions. The left graph displays an experiential learning loop for error solving during scaffold, while the right loop shows how the agent abstracts scaffold-CoTs to generate open-ended solutions.
• Figure 3: Agent K’s performance across Kaggle competitions spanning tabular, computer vision, NLP, and multimodal tasks. The y-axis lists competition IDs; the x-axis shows quantile performance on the private leaderboard (higher is better). Bars with darker shading correspond to Kaggle competitions that granted actual medals as featured or research competitions. On these, Agent K would earn 4 gold and 4 silver medals, and achieve the equivalent of 5 gold, 4 silver, and 12 bronze medals in others.
• Figure 4: Comparison of Agent K's Elo-MMR score with that of human participants. The top plot shows the Elo-MMR distribution of Kaggle users who participated in at least three of the same competitions (7,311 in total). Agent K ranks within the top 18% of this group. Bar colours reflect users’ Kaggle levels at the time of writing. The lower panel breaks down Elo-MMR scores by Kaggle level.
• Figure 5: Performance Comparison of Agent K versus Competing Agents and Foundational Models. (Top Row). We compare Agent K to three ReACT-style agents: ReACT (Qwen), ReACT (Qwen) with RAG, and ReACT (DeepSeek-R1). We also include Agent K (Scaffold Only), which is limited to scaffolded learning environments and does not support open-ended generalisation. We show for each method the distribution of the performance quantiles and the number of medals it achieves, as well as a critical difference diagram among each group of methods. The full Agent K achieves the highest median performance (near the 83 th percentile) and the strongest medal-equivalent record across over 69 tasks: 3 gold (G), 4 silver (S), and 3 bronze (B). (Bottom Row). We benchmark Agent K against a family of TabPFN-v2 models, including both zero-shot and fine-tuned variants. Agent K consistently outperforms all TabPFN-v2 baselines on real-world tabular tasks, where the strongest baseline achieves a 30% median and only 2 gold, 1 silver, and 2 bronze medals. For classification tasks, we additionally compare against TabICL, a long-context in-context learning variant of TabPFN-v2, which performs notably worse than Agent K. These results demonstrate that Agent K’s structured experiential learning architecture enables broad generalisation and competitive performance across diverse data science domains.