Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue

• URL: http://arxiv.org/abs/2608.10626v1
• Date: Tue, 11 Aug 2026 08:14:01 GMT
• Title: Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue
• Abstract summary: Empathetic support is inherently multi-turn and path-dependent.<n>Existing methods evolve the dialogue policy while keeping its training interaction distribution fixed.<n>We introduce a dual-loop self-evolution framework driven by verifiable emotion feedback.
• Score: 25.142249614911208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies [56.86456077356948]
  Frozen-language-action (VLA) policies are increasingly improved at test time.<n>Additional sampling is useful only when better behavior already exists within the policy's rollouts.<n>Retrieval is most useful when the relevant action prior is not reliably represented by the policy.
  arXiv  Detail & Related papers  (2026-08-18T08:11:31Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting [26.620661739354293]
  StanceFlip is a benchmark designed for multimodal conversational stance flipping forecasting over multi-turn dialogues.<n>Our approach achieves state-of-the-art performance on both sextuple extraction and flip-trigger attribution.
  arXiv  Detail & Related papers  (2026-07-27T09:11:56Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• Learning When to Listen: Gated Affect Fusion for Human Motion Prediction [0.0]
  We present a systematic study investigating the utility and temporal limitations of affect-conditioned forecasting in-the-wild.<n>We introduce the Gated Affect Transformer (GAT) to dynamically regulate cross-modal information flow.<n>Our findings provide empirical evidence that facial affect should be regarded as a complementary behavioral cue.
  arXiv  Detail & Related papers  (2026-07-01T00:47:02Z)
• Unlocking Proactivity in Task-Oriented Dialogue [21.99795860301162]
  Proactive task-oriented dialogue (TOD) demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance.<n>We show that conditioning on the user's latent concerns unlocks proactive capability that no amount of sampling can undermine.
  arXiv  Detail & Related papers  (2026-05-21T09:46:25Z)
• EMPA: Evaluating Persona-Aligned Empathy as a Process [2.6558732808569805]
  EMPA is a process-oriented framework that evaluates persona-aligned support as sustained intervention rather than isolated replies.<n>It distills real interactions into controllable, psychologically grounded scenarios.<n>It scores trajectories in a latent psychological space by directional alignment, cumulative impact, and stability.
  arXiv  Detail & Related papers  (2026-02-28T09:04:06Z)
• RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents [67.46032287312339]
  Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess.<n>We introduce RLVER, the first end-to-end reinforcement learning framework that leverages verifiable emotion rewards from simulated users.<n>Our results show that RLVER is a practical route toward emotionally intelligent and broadly capable language agents.
  arXiv  Detail & Related papers  (2025-07-03T18:33:18Z)
• Steering Robots with Inference-Time Interactions [0.5801621787540268]
  When a pretrained policy makes errors during deployment, there are limited mechanisms for users to correct its behavior.<n>My research proposes an alternative: keeping pretrained policies frozen as a fixed skill repertoire while allowing user interactions to guide behavior generation at inference time.<n>Specifically, I propose (1) inference-time steering, which leverages user interactions to switch between discrete skills, and (2) task and motion imitation, which enables user interactions to edit continuous motions while satisfying task constraints defined by discrete symbolic plans.
  arXiv  Detail & Related papers  (2025-06-17T07:59:07Z)
• Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation [82.73098356401725]
  We propose an online reaction policy, called Ready-to-React, to generate the next character pose based on past observed motions.<n>Each character has its own reaction policy as its "brain", enabling them to interact like real humans in a streaming manner.<n>Our approach can be controlled by sparse signals, making it well-suited for VR and other online interactive environments.
  arXiv  Detail & Related papers  (2025-02-27T18:40:30Z)
• Inference-Time Policy Steering through Human Interactions [54.02655062969934]
  During inference, humans are often removed from the policy execution loop.<n>We propose an Inference-Time Policy Steering framework that leverages human interactions to bias the generative sampling process.<n>Our proposed sampling strategy achieves the best trade-off between alignment and distribution shift.
  arXiv  Detail & Related papers  (2024-11-25T18:03:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.