‹ back to 2026-08-17

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

Research LLM Agents

Ranking

Overall 83

Content 100

Popularity 44

Observed public metrics from 1 member.

Merged summary

TL;DR - Envs-FORGE synthesizes difficulty-targeted, reward-verified environments for training terminal agents. It improves agent performance over fixed task-generation recipes while holding training-set size and synthesis scale roughly constant.

Uses estimated seed pass rates and a per-seed MILP to select among six environment-synthesis actions near the learning frontier.
Jointly rewrites instructions, fixtures, oracle solutions, tests, and Docker environments; only gold-verified bundles enter RL training.
On Qwen 3.5 35B, it raises Pass@1 by 9.2 points on tb-core and 6.4 points on tb-2.0 versus Base.
It reaches 77.1% on SWE-bench Verified versus 73.4% for Base and shows gains across evaluated 4B–35B models.

Sources (1)

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

arXiv cs.CL Xiaojun Wu, Cehao Yang, Honghao Liu, Xueyuan Lin, Zhichao Shi, Hao Zhou, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo 2026-08-14 arXiv:2608.14312

Public signals Hugging Face upvotes 0

Providers: Hugging Face · Upvotes 0 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-15 14:32:43.432631 UTC

Uses estimated seed pass rates and a per-seed MILP to select among six environment-synthesis actions near the learning frontier.
Jointly rewrites instructions, fixtures, oracle solutions, tests, and Docker environments; only gold-verified bundles enter RL training.
On Qwen 3.5 35B, it raises Pass@1 by 9.2 points on tb-core and 6.4 points on tb-2.0 versus Base.
It reaches 77.1% on SWE-bench Verified versus 73.4% for Base and shows gains across evaluated 4B–35B models.

item →