agent-environments

Tag

Cards List
#agent-environments

WebAnything: From the Wild Web to Scalable Agent Environments

arXiv cs.AI ↗ · 2026-10-31 Cached

WebAnything presents a fully automated framework that reconstructs source-grounded, reusable web agent environments from real URLs, building 244 website artifacts supporting 12,984 tasks and showing that fine-tuning Qwen3.5-9B on its interaction trajectories improves web agent success rates across multiple benchmarks.

0 favorites 0 likes
#agent-environments

WebAnything: From the Wild Web to Scalable Agent Environments

Hugging Face Daily Papers ↗ · 2026-10-27 Cached

WebAnything 是一个全自动框架,能从真实 URL 重建可复用、源绑定的 Web 环境,用于可扩展的智能体训练与评估。在 244 个网站环境上微调 Qwen3.5-9B,在 REAL、Odysseys 与 WebArena-Verified 基准上取得显著成功率提升。

0 favorites 0 likes
#agent-environments

Scalable Weak-to-Strong Verifier Hardening for Agent Environments

Hugging Face Daily Papers ↗ · 2026-10-11 Cached

提出一种可扩展的弱到强验证器加固循环,通过在隔离沙盒中迭代发现并修复漏洞,自动防止智能体环境的奖励作弊,并在 Terminal Bench、KernelBench 和 SETA 上大幅降低攻击成功率。

0 favorites 0 likes
#agent-environments

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Hugging Face Daily Papers ↗ · 2026-09-18 Cached

RecreationWorld introduces a scalable and verifiable framework for hybrid computer-use agents, providing environments across five platforms and a benchmark for evaluation.

0 favorites 0 likes
#agent-environments

GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments

Hugging Face Daily Papers ↗ · 2026-08-30 Cached

Introduces GUI-CC, a benchmark for evaluating the contextual consistency of GUI world models when used as environments for GUI agents, through offline and online interaction tracks.

0 favorites 0 likes
#agent-environments

@mercor_ai: Agents are only as good as the environments behind them. At Mercor, we've built deep expertise in the realistic, econom…

X AI KOLs Following ↗ · 2026-06-11 Cached

Mercor announces joining the OpenEnv committee alongside Meta, PyTorch, NVIDIA, PrimeIntellect, and Hugging Face to guide the open foundation for agentic environments.

0 favorites 0 likes
#agent-environments

PatchWorld: Gradient-Free Optimization of Executable World Models

arXiv cs.CL ↗ · 2026-06-01 Cached

PatchWorld introduces a gradient-free framework that transforms offline trajectories into executable Python world models via counterexample-guided code repair, enabling interpretable and inspectable belief-state programs for planning in partially observable environments.

0 favorites 0 likes
#agent-environments

SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills

Hugging Face Daily Papers ↗ · 2026-05-22 Cached

SkillEvolBench is a diagnostic benchmark for evaluating whether large language model agents can distill episodic experience into reusable procedural skills. It includes 180 tasks across six environments and finds that current agents often struggle to form robust reusable skills, with raw trajectory reuse often outperforming distilled skills.

0 favorites 0 likes
← Back to home

Submit Feedback