Metraipolis › archive › dc_7b44c7fb401c

ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction — arXiv:2608.20920

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20920
License (as archived)
CC0-1.0
Archived
2026-10-18T10:18:28.143Z
SHA-256 of the archived text
7b7656998e95d3f7713abb26284071155a28f34f957e9dca54ba11ebfdf51b9b
Stable URL of this page
https://metraipolis.com/documento/dc_7b44c7fb401c

How to cite

ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction — arXiv:2608.20920 — arXiv (en), https://arxiv.org/abs/2608.20920 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b44c7fb401c (Metraipolis archive dc_7b44c7fb401c, sha256 7b7656998e95d3f7713abb26284071155a28f34f957e9dca54ba11ebfdf51b9b)
BibTeX
@misc{dc7b44c7fb401c,
  title = {ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction — arXiv:2608.20920},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20920},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b44c7fb401c; sha256 7b7656998e95d3f7713abb26284071155a28f34f957e9dca54ba11ebfdf51b9b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20920. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory mechanisms directly feed retrieved information to agents or rely on simple memory functions such as storing and reusing prior information for prediction, leaving them insufficient for open-web forecasting. We propose to transform raw web evidence into structured memory before prediction, enabling agents to reason over distilled, question-specific evidence rather than noisy retrieval results. This paper presents ForeDreamer, a self-evolving dual-agent framework for managing memory over open-web evidence. ForeDreamer separates factual memory, a question-specific evidence state for the current forecast, from experiential memory, persistent agent experience accumulated across forecasting episodes. It uses a main agent for search and prediction, and a memory-processing subagent to convert search results into factual memory with dedicated tools. ForeDreamer further evolves experiential memory through two tracks, improving both forecasting decisions and factual-memory construction. Experiments on Prophet Arena and FutureX demonstrate the effectiveness of ForeDreamer. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.20920 — 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 2026-10-18T10:17:37.587Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).