Yong Jiang, Xiaobin Wang, Pengjun Xie, Fei Huang, Ningyu Zhang, Huajun Chen, Jialong Wu, Shuofei Qiao, Runnan Fang, Zekun Xi, Yuan Liang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2504.03561")
get_code_for_paper("2504.03561")
have("2504.03561")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2504.03561.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2504.03561)
Connect an agent — have() is free.