environment-synthesis

Tag

Cards List
#environment-synthesis

AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

arXiv cs.CL · 2026-08-24 Cached

AgentMercury introduces a scalable framework for synthesizing verifiable environments from business scenarios, enabling reinforcement learning agents to improve performance on enterprise and out-of-domain benchmarks.

0 favorites 0 likes
#environment-synthesis

@jeongminby98858: New paper Release paper: https://arxiv.org/abs/2608.20634 project: https://minstar.github.io/AgentMercury/index.html… h…

X AI KOLs Timeline · 2026-08-24 Cached

A new research paper introduces AgentMercury, a scalable framework for synthesizing executable environments from business scenarios, which improves agent training performance on various benchmarks.

0 favorites 0 likes
#environment-synthesis

Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL

arXiv cs.CL · 2026-08-17 Cached

Envs-FORGE is a prompting policy for synthesizing training environments for reinforcement learning agents, converting verifier rewards into per-seed actions to improve performance on benchmarks like SWE-bench and Terminal-Bench.

0 favorites 0 likes
#environment-synthesis

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Hugging Face Daily Papers · 2026-05-18 Cached

EnvFactory automates the creation of executable tool environments and natural multi-turn trajectories for training LLMs with agentic reinforcement learning, achieving superior performance on benchmarks like BFCLv3 and MCP-Atlas with fewer environments than prior work.

0 favorites 0 likes
#environment-synthesis

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis

Hugging Face Daily Papers · 2026-05-14 Cached

This paper proposes EvoEnv, a method where language models construct verifiable Python environments for self-improvement through reinforcement learning, achieving a 3.3% relative gain on Qwen3-4B-Thinking.

0 favorites 0 likes
#environment-synthesis

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

arXiv cs.CL · 2026-04-20 Cached

EnvScaler is an automated framework for scaling tool-interactive environments for LLM agents through programmatic synthesis, creating 191 diverse environments and 7K scenarios to improve agent performance on multi-turn, multi-tool interactions.

0 favorites 0 likes
#environment-synthesis

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Hugging Face Daily Papers · 2026-04-20 Cached

Agent-World introduces a self-evolving training framework for general agent intelligence that autonomously discovers real-world environments and tasks via the Model Context Protocol, enabling continuous learning. Agent-World-8B and 14B models outperform strong proprietary models across 23 challenging agent benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback