Scaling Agentic Capabilities via Grounded Interaction Synthesis

• URL: http://arxiv.org/abs/2606.02001v1
• Date: Mon, 01 Jun 2026 09:57:52 GMT
• Title: Scaling Agentic Capabilities via Grounded Interaction Synthesis
• Abstract summary: We introduce Grounded Agentic Interaction Synthesis (GAIS), a framework that automates the scalable construction of diverse environments and complex tasks.<n>Specifically, we construct protocol-anchored environments derived from real-world Model Context Protocol (MCP) servers to ensure functional diversity and difficulty.<n>Experiments on BFCL, $2$-Bench, and ACEBench demonstrate that GAIS-synthesized data significantly outperforms state-of-the-art baselines.
• Score: 12.796216573698677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interaction data. To bypass the prohibitive costs of human annotation, prevailing paradigms depend entirely on Large Language Models (LLMs) to scale the synthesis of agentic environments and tasks. However, such unconstrained generation often degenerates into biased random sampling of LLMs' internal priors, failing to capture the diversity and difficulty of real-world domains or construct high-fidelity, long-horizon tasks. In this work, we introduce Grounded Agentic Interaction Synthesis (GAIS), a framework that automates the scalable construction of diverse environments and complex tasks via a two-phase grounding mechanism. Specifically, we construct protocol-anchored environments derived from real-world Model Context Protocol (MCP) servers to ensure functional diversity and difficulty. Subsequently, we employ structure-guided planning to navigate these environments, actively enforcing logical dependencies and adversarial policies to generate complex tasks. Experiments on BFCL, $τ^2$-Bench, and ACEBench demonstrate that GAIS-synthesized data significantly outperforms state-of-the-art baselines, enabling base models to match or even surpass their official instruction-tuned counterparts. Furthermore, GAIS exhibits superior data efficiency and scalability, achieving exceptional capabilities with significantly less data while maintaining continuous growth where baselines stagnate. Our code and dataset are publicly available at https://github.com/Eric8932/GAIS.

Related papers

• What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents [81.23160457293714]
  LLM agents increasingly rely on generated interaction data to learn how to interact with external environments.<n>Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms.<n>This work develops a two-level framework for the field.
  arXiv  Detail & Related papers  (2026-08-27T15:43:50Z)
• DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows [69.12339622053588]
  We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions.<n>The resulting benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories.<n>We execute these tasks in isolated Docker containers injected with three forms of real-world environmental complexity: Insufficient, Unstable, and Noisy.
  arXiv  Detail & Related papers  (2026-08-27T02:36:23Z)
• ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment [9.28566352356072]
  Andes is a framework that reimagines data generation as a plug-and-play emph agent skill.<n>We demonstrate that Andes improves automated alignment, securing state-of-the-art performance on PostTrainBench.
  arXiv  Detail & Related papers  (2026-05-31T15:03:50Z)
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence [122.8626256816085]
  textbfAgent-World is a self-evolving training arena for advancing general agent intelligence through scalable environments.<n>Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines.
  arXiv  Detail & Related papers  (2026-04-20T14:01:10Z)
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis [30.512393568258105]
  Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data.<n>We propose AgentSkiller, a fully automated framework synthesizing multi-turn interaction data across realistic, semantically linked domains.
  arXiv  Detail & Related papers  (2026-02-10T03:21:42Z)
• Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards [13.784988950752195]
  Existing open-source agentic training data are narrow in task variety and easily solved.<n>Real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes.<n>We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments.
  arXiv  Detail & Related papers  (2026-01-30T03:43:42Z)
• Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction [117.6380005194061]
  We introduce a method designed to systematically scale the diversity and complexity of interactive environments.<n>Our method realizes this scaling by addressing three dimensions.<n>We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure.
  arXiv  Detail & Related papers  (2025-12-04T16:57:02Z)
• CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL [35.086788669916594]
  Large language model based agents are increasingly deployed in complex, tool augmented environments.<n>Existing approaches typically assume predefined task collections, an assumption that fails in novel environments.<n>We propose CuES, a Curiosity driven and Environment grounded Synthesis framework that autonomously generates diverse, executable, and meaningful tasks.
  arXiv  Detail & Related papers  (2025-12-01T06:11:37Z)
• Towards General Agentic Intelligence via Environment Scaling [78.66355092082253]
  Advanced agentic intelligence is a prerequisite for deploying Large Language Models in real-world applications.<n>We design a scalable framework that automatically constructs heterogeneous environments that are fully simulated.<n>Experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.
  arXiv  Detail & Related papers  (2025-09-16T17:57:20Z)
• LEGENT: Open Platform for Embodied Agents [60.71847900126832]
  We introduce LEGENT, an open, scalable platform for developing embodied agents using Large Language Models (LLMs) and Large Multimodal Models (LMMs) LEGENT offers a rich, interactive 3D environment with communicable and actionable agents, paired with a user-friendly interface. In experiments, an embryonic vision-language-action model trained on LEGENT-generated data surpasses GPT-4V in embodied tasks.
  arXiv  Detail & Related papers  (2024-04-28T16:50:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.