mlsanityData to 14 Oct 2026

Towards General Agentic Intelligence via Environment Scaling

arXiv 2509.13311 ↗First posted 16 Sep 2025cs.CLcited by 54

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

Abstract (arXiv)

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.

Key facts. Cited by 54 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 36 of its 47 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

36 of 47 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Small Language Models are the Future of Agentic AI2 Jun
  2. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay4 Apr
  3. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement4 Apr
  4. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments18 Jan
  5. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systems5 Sep
  6. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
  7. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models19 Mar
  8. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep

Other references · 28

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  6. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  7. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  8. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  9. 2023Tool Learning with Foundation Modelscited by 302
  10. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  11. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 229
  12. 2024ToolACE: Winning the Points of LLM Function Callingcited by 216
16 more
  1. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  2. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
  3. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  4. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  5. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
  6. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 132
  7. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  8. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 119
  9. 2025ACEBench: Who Wins the Match Point in Tool Usage?cited by 71
  10. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 68
  11. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Usecited by 50
  12. 2024Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuningcited by 42
  13. 2025Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translationcited by 37
  14. 2025Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environmentscited by 19
  15. 2025StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIscited by 14
  16. 2025DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Modelscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 41.

54 papers.

Sort:

By area:

  1. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 71
  2. 2025Tongyi DeepResearch Technical Reportcited by 66
  3. 2026Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learningcited by 66
  4. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligencecited by 54
  5. 2026ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Trainingcited by 32
  6. 2026Qwen-AgentWorld: Language World Models for General Agentscited by 28
  7. 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL Systemcited by 24
  8. 2025AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learningcited by 20
  9. 2025WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seekingcited by 18
  10. 2026Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Taskscited by 18
  11. 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learningcited by 17
  12. 2025ParallelMuse: Agentic Parallel Thinking for Deep Information Seekingcited by 14
38 more
  1. 2025GTM: Simulating the World of Tools for AI Agentscited by 14
  2. 2026EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RLcited by 14
  3. 2026Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Textcited by 13
  4. 2026DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Usecited by 13
  5. 2026SPADE: Self-Play in Adaptive Synthetic Executable Environmentscited by 12
  6. 2026OVD: On-policy Verbal Distillationcited by 11
  7. 2026OpenComputer: Verifiable Software Worlds for Computer-Use Agentscited by 10
  8. 2025Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scalingcited by 9
  9. 2026AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agentscited by 9
  10. 2026Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Usecited by 8
  11. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  12. 2026LOGIGEN: Logic-Driven Generation of Verifiable Agentic Taskscited by 7
  13. 2026What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?cited by 6
  14. 2026AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesiscited by 6
  15. 2026On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Lengthcited by 6
  16. 2026Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scalecited by 6
  17. 2025SynthTools: A Framework for Scaling Synthetic Tools for Agent Developmentcited by 5
  18. 2026Agent-Omit: Adaptive Context Omission for Efficient LLM Agentscited by 5
  19. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agentscited by 5
  20. 2026ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibrationcited by 4
  21. 2026TopoCurate:Modeling Interaction Topology for Tool-Use Agent Trainingcited by 4
  22. 2025Automating Benchmark Designcited by 3
  23. 2026TRACE: Capability-Targeted Agentic Trainingcited by 3
  24. 2026Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agentscited by 3
  25. 2026MagicAgent: Towards Generalized Agent Planningcited by 2
  26. 2026WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agentscited by 2
  27. 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomycited by 2
  28. 2026Apodex 1.1: Scaling Agentic Intelligence for Complex Workcited by 2
  29. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  30. 2026Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Modelcited by 1
  31. 2026MAVEN: Improving Generalization in Agentic Tool Callingcited by 1
  32. 2026EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agentcited by 1
  33. 2025Structured In-context Environment Scaling for Large Language Model Reasoningcited by 0
  34. 2025On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Datasetcited by 0
  35. 2026Exploring Information Seeking Agent Consolidationcited by 0
  36. 2026Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Taskscited by 0
  37. 2026Behavior Quotient Learning for Low-Rank Adaptation of LLM Agentscited by 0
  38. 2026Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvementcited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Scaling Agentic Capabilities via Grounded Interaction Synthesis
  2. 2025Towards a Science of Scaling Agent Systems
  3. 2025Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
  4. 2026Computer Environments Elicit General Agentic Intelligence in LLMs
  5. 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
  6. 2026Scalable Environments Drive Generalizable Agents
  7. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  8. 2025Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction