Metraipolis › archive › dc_f3402a91d2dd

ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation — arXiv:2608.21925

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21925
License (as archived)
CC0-1.0
Archived
2026-10-18T07:39:06.406Z
SHA-256 of the archived text
82eb690b5f4020bb0a911b36307e9aeac1c49e3d0a9f1bb04120df6ca8a10ecb
Stable URL of this page
https://metraipolis.com/documento/dc_f3402a91d2dd

How to cite

ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation — arXiv:2608.21925 — arXiv (en), https://arxiv.org/abs/2608.21925 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3402a91d2dd (Metraipolis archive dc_f3402a91d2dd, sha256 82eb690b5f4020bb0a911b36307e9aeac1c49e3d0a9f1bb04120df6ca8a10ecb)
BibTeX
@misc{dcf3402a91d2dd,
  title = {ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation — arXiv:2608.21925},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21925},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3402a91d2dd; sha256 82eb690b5f4020bb0a911b36307e9aeac1c49e3d0a9f1bb04120df6ca8a10ecb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21925. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. However, existing methods struggle to simultaneously achieve structured, stage-aware reasoning and seamless empathy-expertise alignment, often resulting in an artificial splicing of clinical strategies and generic reassurance. To overcome these limitations, we propose ESCRAG-R1, a unified framework that integrates retrieval-based psychological guidance into Group Relative Policy Optimization (GRPO). By incorporating retrieval into the reinforcement learning loop, ESCRAG-R1 transforms external knowledge into a robust learning signal that stimulates explicit internal reasoning prior to generation and fundamentally reshapes the model's internal policy. To provide the reliable supervision required for this optimization, we construct ESC-Preference, a high-quality dataset based on a Client--Counselor--Judge evaluation framework that delivers precise, empathy-aware reward signals. Extensive experiments demonstrate that ESCRAG-R1 significantly outperforms existing baselines by mitigating superficial splicing and realizing a natural integration of professional guidance and empathetic expression. Code and datasets are released at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.21925 — 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 2026-10-18T07:37:52.681Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).