Wei Chen, Ruichu Cai, Boyan Xu, Zhifeng Hao, Jiahao Zhang, Keli Zhang, Junjian Ye, Haipeng Zhu
We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| dmirlab-group/causal-aware_llms | canonical | 7 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| build_causal_matrix | Ran | dmirlab-group/causal-aware_llms/parse_utils.py code served (permissive licence) · get_code("ff4801cf2d87f034") |
| episode_len | Ran | dmirlab-group/causal-aware_llms/replay_buffer.py code served (permissive licence) · get_code("6dc883bc1585e237") |
| make_replay_loader | Ran | dmirlab-group/causal-aware_llms/replay_buffer.py code served (permissive licence) · get_code("ba537857289c1d43") |
| parse_causal_description | Ran | dmirlab-group/causal-aware_llms/parse_utils.py code served (permissive licence) · get_code("8a91e975246a4ce3") |
| parse_causal_relation_with_index | Ran | dmirlab-group/causal-aware_llms/parse_utils.py code served (permissive licence) · get_code("20e69de0c3822353") |
| schedule | Ran | dmirlab-group/causal-aware_llms/utils.py code served (permissive licence) · get_code("ae234269debed3f4") |
| to_torch | Ran | dmirlab-group/causal-aware_llms/utils.py code served (permissive licence) · get_code("c8852f15bf8f5c93") |
| load_episode | Not yet run | dmirlab-group/causal-aware_llms/replay_buffer.py code served (permissive licence) · get_code("e4add8e350037eb9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) have shown great potential in decision-making due to the vast amount of knowledge stored within the models. However, these pre-trained models are prone to lack reasoning abilities and are difficult to adapt to new environments, further hindering their application to complex real-world tasks. To address these challenges, inspired by the human cognitive process, we propose Causal-aware LLMs, which integrate the structural causal model (SCM) into the decision-making process to model, update, and utilize structured knowledge of the environment in a "learning-adapting-acting" paradigm. Specifically, in the learning stage, we first utilize an LLM to extract the environment-specific causal entities and their causal relations to initialize a structured causal model of the environment. Subsequently, in the adapting stage, we update the structured causal model through external feedback about the environment, via an idea of causal intervention. Finally, in the acting stage, Causal-aware LLMs exploit structured causal knowledge for more efficient policymaking through the reinforcement learning agent. The above processes are performed iteratively to learn causal knowledge, ultimately enabling the causal-aware LLMs to achieve a more accurate understanding of the environment and make more efficient decisions. Experimental results across 22 diverse tasks within the open-world game "Crafter" validate the effectiveness of our proposed method.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2505.24710")
get_code_for_paper("2505.24710")
have("2505.24710")
Connect an agent — have() is free.