mlsanityData to 7 Oct 2026

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

arXiv 2410.02810 ↗First posted 21 Sep 2024cs.AI cs.CL cs.LGcited by 21

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

Abstract (arXiv)

Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying base agent. Existing methods, however, struggle with long-context reasoning and goal adherence. We introduce StateAct, a novel and efficient base agent that enhances decision-making through (1) self-prompting, which reinforces task goals at every step, and (2) chain-of-states, an extension of chain-of-thought that tracks state information over time. StateAct outperforms ReAct, the previous best base agent, by over 10% on Alfworld, 30% on Textcraft, and 7% on Webshop across multiple frontier LLMs. We also demonstrate that StateAct can be used as a drop-in replacement for ReAct with advanced LLM agent methods such as test-time scaling, yielding an additional 12% gain on Textcraft. By improving efficiency and long-range reasoning without requiring additional training or retrieval, StateAct provides a scalable foundation for LLM agents. We open source our code to support further research at https://github.com/ai-nikolai/stateact .

Key facts. Cited by 21 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 24 of its 39 references that are in the map. First posted on arXiv 21 Sep 2024.

Builds on

24 of 39 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy21 Mar
  2. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  8. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  9. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  10. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  11. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  12. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
10 more
  1. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  2. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  3. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  4. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  5. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  6. 2020Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformerscited by 57
  7. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  8. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 24
  9. 2024Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrievalcited by 13
  10. 2023Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actorscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 17.

21 papers.

Sort:

By area:

  1. 2025Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agentscited by 14
  2. 2026Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertaintycited by 8
  3. 2026Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Taskscited by 7
  4. 2025Fine-tuning with RAG for Improving LLM Learning of New Skillscited by 5
  5. 2026Mitigating Conversational Inertia in Multi-Turn Agentscited by 5
  6. 2026LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agentscited by 4
  7. 2026The Context Gathering Decision Process: A POMDP Framework for Agentic Searchcited by 4
  8. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 4
  9. 2026Kintsugi: Learning Policies by Repairing Executable Knowledge Basescited by 3
  10. 2025Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulationscited by 2
  11. 2026Reward Prediction with Factorized World Statescited by 2
  12. 2026Self-Optimizing Multi-Agent Systems for Deep Researchcited by 2
9 more
  1. 2026When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agentscited by 2
  2. 2026Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agentscited by 1
  3. 2026Can LLM Agents Infer World Models? Evidence from Agentic Automata Learningcited by 1
  4. 2026The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMscited by 1
  5. 2025Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Tradingcited by 0
  6. 2026The FIL Hypothesis: Inductive Biases Help with Kernel Engineeringcited by 0
  7. 2026Towards a Belief-Based World Model for LLM Agentscited by 0
  8. 2026FlowState: Execution State as Memory for Long-Horizon LLM Agentscited by 0
  9. 2026Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief Statescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
  2. 2024AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents
  3. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Survey
  4. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  5. 2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
  6. 2023A Survey on Large Language Model based Autonomous Agents
  7. 2026LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
  8. 2023LASER: LLM Agent with State-Space Exploration for Web Navigation