Metraipolis › archive › dc_2e736204ddb8
CauProphet: Teaching Agents to Develop Causal Cognition like Humans — arXiv:2610.32477
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32477
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:50:40.119Z
- SHA-256 of the archived text
8dfabffd16230262a605885bc7a0c780566988d08f279fd119c5f52a326e4126- Stable URL of this page
https://metraipolis.com/documento/dc_2e736204ddb8
How to cite
CauProphet: Teaching Agents to Develop Causal Cognition like Humans — arXiv:2610.32477 — arXiv (en), https://arxiv.org/abs/2610.32477 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e736204ddb8 (Metraipolis archive dc_2e736204ddb8, sha256 8dfabffd16230262a605885bc7a0c780566988d08f279fd119c5f52a326e4126)
BibTeX
@misc{dc2e736204ddb8,
title = {CauProphet: Teaching Agents to Develop Causal Cognition like Humans — arXiv:2610.32477},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32477},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e736204ddb8; sha256 8dfabffd16230262a605885bc7a0c780566988d08f279fd119c5f52a326e4126},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32477. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly support long-horizon tasks by leveraging external memory and past experience. However, existing agents mainly retrieve records or summaries, lacking the ability to form and refine causal understanding of the world. Inspired by human causal cognition, we introduce CauProphet, an agent that develops and updates causal knowledge within its Causal Cognition. For each task, CauProphet combines relevant knowledge in Causal Cognition with current evidence to construct a Causal Belief, a structured belief capturing causal factors and the effects of possible actions. It uses this belief for decision-making and continuously updates both the belief and Causal Cognition as new observations emerge, enabling causal knowledge that persists beyond individual experiences. Evaluations demonstrate that CauProphet progressively acquires causal knowledge and transfers it to future decision-making. In financial research, CauProphet leverages prior discoveries to improve downstream analyses and outperforms all baselines in mean rank correlation with next-day returns, achieving a 25.4% improvement over a baseline agent. It also improves prediction accuracy from 21.3% to 28.6% in dynamic real-world settings. Further experiments validate its ability to perform reliable causal analysis and action selection across scientific and everyday tasks, demonstrating the potential of causal experience learning for next-generation LLM agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.32477 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-26T19:45:33.319Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).