SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting agents with scalable real-world services, but training robust agents remains limited by the lack of realistic environments and principled mechanisms for life-long learning. In this paper, we present \textbf{Agent-World}, a self-evolving training arena for advancing general agent intelligence through scalable environments. Agent-World has two main components: (1) Agentic Environment-Task Discovery, which autonomously explores topic-aligned databases and executable tool ecosystems from thousands of real-world environment themes and synthesizes verifiable tasks with controllable difficulty; and (2) Continuous Self-Evolving Agent Training, which combines multi-environment reinforcement learning with a self-evolving agent arena that automatically identifies capability gaps through dynamic task synthesis and drives targeted learning, enabling the co-evolution of agent policies and environments. Across 23 challenging agent benchmarks, Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines. Further analyses reveal scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.
citation-role summary
background 3
citation-polarity summary
years
2026 10roles
background 2polarities
background 2representative citing papers
OpenFinGym is a multi-task verifiable gym environment for quant-finance agents with automated task construction from publications, containerised runtime, paper trading engine, and support for SFT/RL training.
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
The paper presents OverEager-Gen, a 500-scenario benchmark showing that removing consent declarations from prompts increases overeager actions by 11.9-17.2 percentage points across models, with agent framework choice dominating base-model effects.
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
AFTER benchmark shows single refinement improves LLM agent performance by 3.7-6.7 points and multi-model procedural skills reach 73.1% cross-model accuracy on 382 tasks.
PhoneBuddy combines real-app and mock-app RL after shared SFT, raising real-phone task success from 36.67% to 45.33% and AndroidWorld from 60.3% to 83.2%.
PhoneWorld is a pipeline that converts real mobile trajectories into scalable controllable environments, yielding large gains on four benchmarks when used to supplement training data.
Generalizable agents require environment scaling via diverse executable rule-sets, distinguished from trajectory and task scaling in a new taxonomy.
citing papers explorer
No citing papers match the current filters.