# Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

arXiv: https://arxiv.org/abs/2512.16301 · HTML: https://mlsanity.com/paper/2512.16301/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 176 of its 409 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 176)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)

## Built on by (most cited first, 22 of 22)

- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2605.01293/) (2026)
- [An Information Theoretic Perspective on Agentic System Design](https://mlsanity.com/paper/2512.21720/) (2025)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.03689/) (2026)
- [ElasticMem: Latent Memory as a Learnable Resource for LLM Agents](https://mlsanity.com/paper/2605.30690/) (2026)
- [Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents](https://mlsanity.com/paper/2602.01415/) (2026)
- [daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently](https://mlsanity.com/paper/2602.02619/) (2026)
- [Interactive Evaluation Requires a Design Science](https://mlsanity.com/paper/2605.17829/) (2026)
- [Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?](https://mlsanity.com/paper/2607.07548/) (2026)
- [ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents](https://mlsanity.com/paper/2605.30712/) (2026)
- [Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering](https://mlsanity.com/paper/2607.25090/) (2026)
- [Heterogeneous Scientific Foundation Model Collaboration](https://mlsanity.com/paper/2604.27351/) (2026)
- [Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior](https://mlsanity.com/paper/2606.12730/) (2026)
- [Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion](https://mlsanity.com/paper/2603.06397/) (2026)
- [The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents](https://mlsanity.com/paper/2605.10754/) (2026)
- [When AI meets quantum information: A comprehensive review](https://mlsanity.com/paper/2607.00365/) (2026)
- [LifeMem: Enabling Lifelong Experience Reuse for LLM Agents](https://mlsanity.com/paper/2609.12655/) (2026)
- [FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents](https://mlsanity.com/paper/2609.34358/) (2026)
- [Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval](https://mlsanity.com/paper/2610.14465/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of adaptation: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.