# DynaSaur: Large Language Agents Beyond Predefined Actions

arXiv: https://arxiv.org/abs/2411.01747 · HTML: https://mlsanity.com/paper/2411.01747/

## Key facts

- Cited by 32 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 39 of its 57 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## 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 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets](https://mlsanity.com/paper/2309.17428/) (2023)

## Built on by (most cited first, 30 of 32)

- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [GUI Agents: A Survey](https://mlsanity.com/paper/2412.13501/) (2024)
- [How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings](https://mlsanity.com/paper/2604.04323/) (2026)
- [Towards Trustworthy GUI Agents: A Survey](https://mlsanity.com/paper/2503.23434/) (2025)
- [ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2603.16060/) (2026)
- [Aviary: training language agents on challenging scientific tasks](https://mlsanity.com/paper/2412.21154/) (2024)
- [COLA: A Scalable Multi-Agent Framework For Windows UI Task Automation](https://mlsanity.com/paper/2503.09263/) (2025)
- [Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization](https://mlsanity.com/paper/2502.01562/) (2025)
- [Co-Evolving Agents: Learning from Failures as Hard Negatives](https://mlsanity.com/paper/2511.22254/) (2025)
- [A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users](https://mlsanity.com/paper/2509.18632/) (2025)
- [ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization](https://mlsanity.com/paper/2603.22791/) (2026)
- [Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation](https://mlsanity.com/paper/2605.09315/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [OWLViz: An Open-World Benchmark for Visual Question Answering](https://mlsanity.com/paper/2503.07631/) (2025)
- [LLM Library Learning Fails: A LEGO-Prover Case Study](https://mlsanity.com/paper/2504.03048/) (2025)
- [CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory](https://mlsanity.com/paper/2512.15813/) (2025)
- [Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security](https://mlsanity.com/paper/2507.19399/) (2025)
- [Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents](https://mlsanity.com/paper/2608.20274/) (2026)
- [Program Synthesis Dialog Agents for Interactive Decision-Making](https://mlsanity.com/paper/2502.19610/) (2025)
- [Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems](https://mlsanity.com/paper/2508.15411/) (2025)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [On the Creativity of AI Agents](https://mlsanity.com/paper/2604.13242/) (2026)
- [Rethinking Agentic Reinforcement Learning In Large Language Models](https://mlsanity.com/paper/2604.27859/) (2026)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)
- [MALBO: Optimizing LLM-Based Multi-Agent Teams via Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2511.11788/) (2025)
- [Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation](https://mlsanity.com/paper/2512.20278/) (2025)
- [Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows](https://mlsanity.com/paper/2606.14672/) (2026)
- [Workload-Aware Caching for Multi-Agent Systems](https://mlsanity.com/paper/2607.20495/) (2026)
- [CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs](https://mlsanity.com/paper/2608.00018/) (2026)
- [ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions](https://mlsanity.com/paper/2608.26991/) (2026)

## Abstract (arXiv)

Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly scoped environments, it presents two major challenges for real-world, open-ended scenarios: (1) it significantly restricts the planning and acting capabilities of LLM agents, and (2) it requires substantial human effort to enumerate and implement all possible actions, which is impractical in complex environments with a vast number of potential actions. To address these limitations, we propose an LLM agent framework that can dynamically create and compose actions as needed. In this framework, the agent interacts with its environment by generating and executing programs written in a general-purpose programming language. Moreover, generated actions are accumulated over time for future reuse. Our extensive experiments across multiple benchmarks show that this framework significantly improves flexibility and outperforms prior methods that rely on a fixed action set. Notably, it enables LLM agents to adapt and recover in scenarios where predefined actions are insufficient or fail due to unforeseen edge cases. Our code can be found in https://github.com/adobe-research/dynasaur.