mlsanityData to 7 Oct 2026

Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows

arXiv 2602.14849 ↗First posted 16 Feb 2026cs.LG cs.AI cs.DCcited by 27

Not on the map. Why?

Cited by 20 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and concurrent agents can leave partial effects, losing-branch residue, stale writes, or irreversible sends. Correct settlement needs two facts that retries, checkpoint replay, locks, and compensation each conflate: which effects must settle together, and when earlier conflicting work is exhausted. Atomix makes this split explicit with progress-aware transactions. The runtime records reads and effects during execution, seals a transaction when its footprint is complete, and commits only after per-resource frontiers show that no earlier conflicting work can still arrive. Commit is final settlement: Atomix releases bufferable effects, accepts reversible external effects as final, and lets irreversible effects leave the gate. Abort suppresses unreleased effects and compensates externalized reversible effects where possible. On representative agent workloads, this composition improves clean recovery under injected faults, isolates contending and speculative work, and prevents correctly classified irreversible actions from leaking; microbenchmarks show microsecond-scale wrapper overhead relative to tool latency.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 23 of its 57 references that are in the map. First posted on arXiv 16 Feb 2026.

Builds on

23 of 57 references.

References · 23

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  5. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  6. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  7. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  10. 2024AIOS: LLM Agent Operating Systemcited by 94
  11. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  12. 2024DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processingcited by 49
11 more
  1. 2024A Declarative System for Optimizing AI Workloadscited by 35
  2. 2025SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systemscited by 23
  3. 2024GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applicationscited by 22
  4. 2025Get Experience from Practice: LLM Agents with Record & Replaycited by 22
  5. 2025Speculative Actions: A Lossless Framework for Faster Agentic Systemscited by 20
  6. 2024Asynchronous LLM Function Callingcited by 18
  7. 2025Sherlock: Reliable and Efficient Agentic Workflow Executioncited by 10
  8. 2025AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systemscited by 8
  9. 2025ALAS: Transactional and Dynamic Multi-Agent LLM Planningcited by 3
  10. 2021Serverless Workflows with Durable Functions and Netheritecited by 2
  11. 2026PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Usecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 27.

27 papers.

Sort:

By area:

  1. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  2. 2026TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memorycited by 7
  3. 2026Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systemscited by 5
  4. 2026SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflowscited by 3
  5. 2026ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesiscited by 3
  6. 2026SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inferencecited by 3
  7. 2026Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitivescited by 3
  8. 2026Agentic Transaction: Towards ACID-Compliant Agent Systemscited by 3
  9. 2026Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contextscited by 2
  10. 2026Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollbackcited by 2
  11. 2026Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systemscited by 2
  12. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 1
15 more
  1. 2026When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authoritycited by 1
  2. 2026REPOT: Recoverable Program-of-Thought via Checkpoint Repaircited by 0
  3. 2026Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Toolscited by 0
  4. 2026Stateful Governance for Concurrent Agentic Systemscited by 0
  5. 2026Callability Is Not Operability: Controlled Interface Interventions for LLM Agentscited by 0
  6. 2026The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systemscited by 0
  7. 2026REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflowscited by 0
  8. 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBoundcited by 0
  9. 2026When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundarycited by 0
  10. 2026LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agentscited by 0
  11. 2026Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agentscited by 0
  12. 2026Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Racescited by 0
  13. 2026Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflowscited by 0
  14. 2026TomasuLLM: Out-of-Order Speculative Execution for LLM Agentscited by 0
  15. 2026Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows
  2. 2026Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
  3. 2026AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
  4. 2026ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
  5. 2026Correct Is Not Governed: Provenance Integrity in Agentic Workflows
  6. 2026ControlScope: Workflow Revision and Reliability in LLM Agents
  7. 2026AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?
  8. 2026Cordon: Semantic Transactions for Tool-Using LLM Agents