mlsanityData to 7 Oct 2026

TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON

arXiv 2407.15734 ↗First posted 22 Jul 2024cs.AI cs.MAcited by 5

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token usage), TaskGen uses StrictJSON that ensures JSON output from the Large Language Model (LLM), along with additional features such as type checking and iterative error correction. Key to the philosophy of TaskGen is the management of information/memory on a need-to-know basis. We empirically evaluate TaskGen on various environments such as 40x40 dynamic maze navigation with changing obstacle locations (100% solve rate), TextWorld escape room solving with dense rewards and detailed goals (96% solve rate), web browsing (69% of actions successful), solving the MATH dataset (71% solve rate over 100 Level-5 problems), Retrieval Augmented Generation on NaturalQuestions dataset (F1 score of 47.03%)

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 18 of its 26 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

18 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  7. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  10. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  11. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  12. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 302
5 more
  1. 2023Effective Long-Context Scaling of Foundation Modelscited by 301
  2. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  3. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  4. 2023GPT Can Solve Mathematical Problems Without a Calculatorcited by 68
  5. 2023Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environmentscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  2. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  3. 2025HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worldscited by 6
  4. 2024Generating a Low-code Complete Workflow via Task Decomposition and RAGcited by 3
  5. 2026Software-Defined Agentic Servingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025TaskCraft: Automated Generation of Agentic Tasks
  2. 2025Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent Tasks
  3. 2025AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
  4. 2026SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
  5. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  6. 2026SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
  7. 2026EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
  8. 2026MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents