mlsanityData to 14 Oct 2026

ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning

arXiv 2505.12501 ↗First posted 18 May 2025cs.AIcited by 5

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

Abstract (arXiv)

Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time disruption recovery. We present Adaptive LLM Agent System (ALAS), a framework that tackles four fundamental LLM deficits: (i) absence of self-verification, (ii) context erosion, (iii) next-token myopia, and (iv) lack of persistent state. ALAS decomposes each plan into role-specialized agents, equips them with automatic state tracking, and coordinates them through a lightweight protocol. When disruptions arise, agents apply history-aware local compensation, avoiding costly global replanning and containing cascade effects. On real-world, large-scale job-shop scheduling benchmarks, ALAS sets new best results for static sequential planning and excels in dynamic reactive scenarios with unexpected disruptions. These gains show that principled modularization plus targeted compensation can unlock scalable and resilient planning with LLMs.

Key facts. Cited by 5 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 48 of its 84 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

48 of 84 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks26 Feb
  2. 2024Understanding the planning of LLM agents: A survey5 Feb
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  10. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  11. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  12. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
32 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  3. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  4. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  5. 2025Why Do Multi-Agent LLM Systems Fail?cited by 604
  6. 2024Large Language Models: A Surveycited by 525
  7. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  8. 2023Larger language models do in-context learning differentlycited by 394
  9. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  10. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspectivecited by 294
  11. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  12. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  13. 2023Efficient Large Language Models: A Surveycited by 186
  14. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  15. 2020Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learningcited by 140
  16. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  17. 2024Large Language Models Can Learn Temporal Reasoningcited by 111
  18. 2023Why think step by step? Reasoning emerges from the locality of experiencecited by 103
  19. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 103
  20. 2024Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilizationcited by 101
  21. 2023Context-faithful Prompting for Large Language Modelscited by 80
  22. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  23. 2023Prompting Large Language Models With the Socratic Methodcited by 43
  24. 2025A Survey on Large Language Models with some Insights on their Capabilities and Limitationscited by 42
  25. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  26. 2023TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Modelscited by 39
  27. 2024ACPBench: Reasoning about Action, Change, and Planningcited by 39
  28. 2024LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environmentscited by 36
  29. 2024Evaluating Creative Short Story Generation in Humans and Large Language Modelscited by 21
  30. 2025Starjob: Dataset for LLM-Driven Job Shop Schedulingcited by 12
  31. 2024Automatic programming via large language models with population self-evolution for dynamic fuzzy job shop scheduling problemcited by 10
  32. 2018Boosting Binary Optimization via Binary Classification: A Case Study of Job Shop Schedulingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Factscited by 13
  2. 2026DART: Semantic Recoverability for Structured Tool Agentscited by 10
  3. 2026DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolutioncited by 1
  4. 2026A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agentscited by 0
  5. 2026A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AIcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ALAS: Transactional and Dynamic Multi-Agent LLM Planning
  2. 2025Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
  3. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
  4. 2024Practical Considerations for Agentic LLM Systems
  5. 2026From Task Solving to Robust Real-World Adaptation in LLM Agents
  6. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  7. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents
  8. 2026Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents