mlsanityData to 7 Oct 2026

Grounded Scaling: Why Agentic AI Needs Deterministic Environments

arXiv 2606.22495 ↗First posted 21 Jun 2026cs.AIcited by 0

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

Abstract (arXiv)

Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-step determinism δ < 1, k-step chain success degrades as δk. The AGI-to-ASI scaling debate (Genewein et al., 2026) has so far framed progress as a race between compute growth and a list of frictions (data wall, abstraction barrier, embodied bottleneck, multi-agent trust); we argue that environment determinism is a complementary binding axis cutting across all four, for the broad class of agentic AI tasks whose outcomes are verifiable economically, physically, or through multi-party settlement. Three formal results pin down the regime: a Determinism-Efficiency Bound on chain-task success, a Verifier-Goodharting Floor on flywheel ceilings under imperfect rewards, and a convergence condition for environment-side skill evolution. We operationalise the framework as a Supply Certainty Index (SCI) over five measurable properties, a five-level Determinism Maturity Model (DMM) as adoption ladder, and a falsifiable open-question programme (OQ1-OQ5) with explicit null results that would force retraction. The position is platform-agnostic. We engage three competing positions: sim-to-real sufficiency, alignment sufficiency, and AI-as-normal-technology.

Key facts. No citing papers in the map yet (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 69 of its 126 references that are in the map. First posted on arXiv 21 Jun 2026.

Builds on

69 of 126 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning22 Mar
  2. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents29 May
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 65

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  10. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  11. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  12. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
38 more
  1. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  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. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  6. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  9. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  10. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  11. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  12. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  13. 2019Solving Rubik's Cube with a Robot Handcited by 699
  14. 2018Learning Dexterous In-Hand Manipulationcited by 643
  15. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  16. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  17. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  18. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
  19. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 475
  20. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  21. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  22. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  23. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  24. 2023An Overview of Catastrophic AI Riskscited by 214
  25. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decodingcited by 198
  26. 2022Will we run out of data? Limits of LLM scaling based on human-generated datacited by 187
  27. 2022Compute Trends Across Three Eras of Machine Learningcited by 161
  28. 2025Multi-Agent Risks from Advanced AIcited by 150
  29. 2023Self-Alignment with Instruction Backtranslationcited by 149
  30. 2024Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Datacited by 143
  31. 2018Supervising strong learners by amplifying weak expertscited by 139
  32. 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 137
  33. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  34. 2024A Tale of Tails: Model Collapse as a Change of Scaling Lawscited by 127
  35. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 122
  36. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  37. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 89
  38. 2022SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapterscited by 83

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
  2. 2025Towards a Science of Scaling Agent Systems
  3. 2026Scalable Environments Drive Generalizable Agents
  4. 2025CORE: Full-Path Evaluation of LLM Agents Beyond Final State
  5. 2026Apodex 1.1: Scaling Agentic Intelligence for Complex Work
  6. 2026Position: Agentic AI System Is a Foreseeable Pathway to AGI
  7. 2026Beyond Scaling: Agents Are Heading to the Edge
  8. 2025Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems