by rhyang2021 · Agent Tool · ★ 26
ARIA: Training Language Agents with Intention-Driven Reward Aggregation Ruihan Yang1  Yikai Zhang1  Aili Chen1  1Fudan University Introduction Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an extremely large and combinatorial action space.
| Stars | 26 |
| Forks | 2 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 65.1396296722317/100 |
| Open Issues | 1 |
| Last Updated | 2025-08-09 |
| Created | 2025-05-26 |
| Platforms | python |
| Est. Tokens | ~457k |
Explore other popular agent tool tools:
ARIA is Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".. It is categorized as a Agent Tool with 26 GitHub stars.
ARIA is primarily written in Python. It covers topics such as langauge-model, llm-agent.
You can find installation instructions and usage details in the ARIA GitHub repository at github.com/rhyang2021/ARIA. The project has 26 stars and 2 forks, indicating an active community.