Metraipolis › archive › dc_cc1ea8299c5c
Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue — arXiv:2608.10626
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10626
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:14:13.968Z
- SHA-256 of the archived text
531fc183b88b6f87b09bb506a6a0b21e3e7b616d874247f09a703151c47986ba- Stable URL of this page
https://metraipolis.com/documento/dc_cc1ea8299c5c
How to cite
Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue — arXiv:2608.10626 — arXiv (en), https://arxiv.org/abs/2608.10626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc1ea8299c5c (Metraipolis archive dc_cc1ea8299c5c, sha256 531fc183b88b6f87b09bb506a6a0b21e3e7b616d874247f09a703151c47986ba)
BibTeX
@misc{dccc1ea8299c5c,
title = {Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue — arXiv:2608.10626},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10626},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc1ea8299c5c; sha256 531fc183b88b6f87b09bb506a6a0b21e3e7b616d874247f09a703151c47986ba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently multi-turn and path-dependent: users disclose concerns gradually, emotions evolve over time, and early responses shape trust and receptivity. Reinforcement learning with verifiable emotion rewards provides scalable supervision for long-horizon interactions. However, existing methods evolve the dialogue policy while keeping its training interaction distribution fixed, creating a mismatch between policy competence and training experience. We introduce a dual-loop self-evolution framework driven by verifiable emotion feedback. With the user simulator and verifier frozen, the inner loop optimizes the multi-turn policy using continuous emotion rewards, while the outer loop uses the same outcomes to estimate policy-relative interaction utility and adapt experience. To obtain estimates from sparse, stochastic rollouts, the framework holds the scenario and interaction state constant within each group and prioritizes conditions whose group pass rates lie near the policy's competence boundary. A hierarchical controller shares evidence across support intents, while uncertainty-guided exploration and uniform rehearsal prevent premature exclusion. The resulting distribution generates trajectories, closing both loops without increasing the rollout budget. On SAGE, our framework raises Qwen3-8B Overall from 53.87 to 79.24 and outperforms protocol-matched uniform emotion-reward reinforcement learning by 7.23 points. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.10626 — 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 2026-10-19T06:08:50.321Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).