ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations

• URL: http://arxiv.org/abs/2605.27908v1
• Date: Wed, 27 May 2026 03:32:12 GMT
• Title: ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
• Abstract summary: We propose ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills.<n>We first model localized support interactions as Intervention Units (IUs), which capture state--action-outcome dynamics between seeker states, support interventions, and post-response emotional changes.<n>We construct the ESC-Skills Bank, a repository of executable emotional support skills containing intervention guidance, applicability conditions, expected outcomes, and potential risks.
• Score: 25.708317827505695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little support for systematic skill improvement. We propose ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills. We first model localized support interactions as Intervention Units (IUs), which capture state--action--outcome dynamics between seeker states, support interventions, and post-response emotional changes. Based on IUs extracted from both successful and failed ESC dialogues, we construct the ESC-Skills Bank, a repository of executable emotional support skills containing intervention guidance, applicability conditions, expected outcomes, and potential risks. To further improve robustness, we introduce a multi-profile self-evolutionary refinement framework in which an ESC agent interacts with diverse simulated seeker profiles under SAGE evaluation. The resulting interaction traces are analyzed to identify missing skills, unsafe interventions, and profile-specific failure patterns, which are then used to refine the Skills Bank through simulation-based verification. Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC-Skills Bank at https://github.com/aliyun/qwen-dianjin.

Related papers

• Coalition-Aware Skill Reliability for Self-Evolving Agents [49.43736235959317]
  We investigate whether accumulated skills in an agent's skill bank actually make positive mechanistic contributions.<n>We show that coalition pollution, where bank-level gains conceal negative coalition-level skill contributions, and cross-domain utility reversal, where source-beneficial skills reverse their effects after transfer.<n>These findings motivate two reliability interventions: coalition-aware skill selection during skill accumulation and label-free skill masking after transfer.
  arXiv  Detail & Related papers  (2026-08-23T21:35:22Z)
• 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)
• Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation [12.273252267253385]
  We build the first dataset that expands existing ESC datasets by adding labels for cognitive distortions.<n>We propose the Cognitive Policy-driven Large Language Model framework (CoPoLLM) to enhance LLMs' ability to diagnose and intervene cognitive distortions in help-seekers.<n> Experimental results show that CoPoLLM significantly outperforms 15 state-of-the-art baselines in terms of distortion diagnosis accuracy, intervention strategy effectiveness, and safety risk control.
  arXiv  Detail & Related papers  (2026-04-19T00:39:04Z)
• AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models [0.0]
  We introduce the Adversarial Resource Extraction Game (AREG), a benchmark that operationalizes persuasion and resistance as a multi-turn, zero-sum negotiation over financial resources.<n>Using a round-robin tournament across frontier models, AREG enables joint evaluation of offensive (persuasion) and defensive (resistance) capabilities.
  arXiv  Detail & Related papers  (2026-02-18T17:28:28Z)
• CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation [25.567786529759406]
  Emotional Support Conversation (ESC) plays a vital role in alleviating psychological stress and providing emotional value through dialogue.<n>Recent studies have largely focused on data augmentation and synthetic corpus construction.<n>We propose textbfCARE, a novel framework that strengthens reasoning in ESC without relying on large-scale synthetic data.
  arXiv  Detail & Related papers  (2025-09-30T03:19:50Z)
• Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards [13.938394655357916]
  Emotional Support Conversation systems aim to alleviate users' emotional difficulties and provide long-term, systematic support for emotional well-being.<n>Most large language model (LLM)-based ESC systems rely on predefined strategies, which limits their effectiveness in complex, real-life scenarios.<n>This paper introduces a novel end-to-end framework (RLFF-ESC) that directly learns enduring emotionally supportive response skills using reinforcement learning.
  arXiv  Detail & Related papers  (2025-08-18T14:04:26Z)
• IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems [74.0855067343594]
  In emotional support conversations, unclear intentions can lead supporters to employ inappropriate strategies.<n>We propose the Intention-centered Emotional Support Conversation framework.<n>It defines the possible intentions of supporters, identifies key emotional state aspects for inferring these intentions, and maps them to appropriate support strategies.
  arXiv  Detail & Related papers  (2025-06-06T10:14:49Z)
• Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models [70.180385882195]
  This paper introduces a personality-aware user simulation for Conversational Recommender Systems (CRSs)<n>The user agent induces customizable personality traits and preferences, while the system agent possesses the persuasion capability to simulate realistic interaction in CRSs.<n> Experimental results demonstrate that state-of-the-art LLMs can effectively generate diverse user responses aligned with specified personality traits.
  arXiv  Detail & Related papers  (2025-04-09T13:21:17Z)
• EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery [65.30120701878582]
  Large Language Model (LLM) agents are vulnerable to exploitation in emotion-sensitive domains like debt collection.<n>EmoDebt is an emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem.<n>EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines.
  arXiv  Detail & Related papers  (2025-03-27T01:41:34Z)
• FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models [14.894922829587841]
  Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures. Current non-artificial methodologies face challenges in effectively appraising the emotional support capability. We propose a novel model FEEL, employing Large Language Models (LLMs) as evaluators to assess emotional support capabilities.
  arXiv  Detail & Related papers  (2024-03-23T03:32:26Z)
• K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning [83.19215082550163]
  We propose K-ESConv, a novel prompt learning based knowledge injection method for emotional support dialogue system. We evaluate our model on an emotional support dataset ESConv, where the model retrieves and incorporates knowledge from external professional emotional Q&A forum.
  arXiv  Detail & Related papers  (2023-12-16T08:10:10Z)
• Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach [58.88422314998018]
  Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state. Existing works stay at fitting grounded responses and responding strategies which ignore the effect on ES and lack explicit goals to guide emotional positive transition. We introduce a new paradigm to formalize multi-turn ESC as a process of positive emotion elicitation.
  arXiv  Detail & Related papers  (2023-07-16T09:58:44Z)
• Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning [81.79431311952656]
  We propose a novel system MultiESC to provide Emotional Support. For strategy planning, we propose lookaheads to estimate the future user feedback after using particular strategies. For user state modeling, MultiESC focuses on capturing users' subtle emotional expressions and understanding their emotion causes.
  arXiv  Detail & Related papers  (2022-10-09T12:23:47Z)

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.