EmoDistill is an offline framework that distills emotional negotiation skills from large language model interactions into smaller agents. It separates emotion selection, handled by an Implicit Q‑Learning selector, from emotion‑conditioned expression, learned by a LoRA‑adapted 7B policy via supervised fine‑tuning and judge policy optimization. Experiments across four negotiation domains show that the full EmoDistill policy outperforms vanilla and IQL‑only baselines, while removing the explicit emotion channel markedly reduces negotiation utility and reveals partial, domain‑dependent transfer to unseen counterparties.
arXiv:2608. 09248v1 Announce Type: new Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved.
Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved. Recent interpretability work has shown that LLMs maintain linear emotion representations that causally influence behavior; however, these representations have been exploited only for post-hoc analysis or direct output steering, and have not been used to inform agent-level decision-making.
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We st...
The paper introduces CASE, a Confusion-Aware Skill Evolution framework designed to improve Multimodal Emotion Recognition (MER) by addressing systematic confusion between semantically adjacent emotions. CASE builds a sparse, self‑evolving library of pair‑specific EmotionSkills that externalize affective expertise from frozen multimodal large language model (MLLM) backbones, allowing continuous refinement and transfer across different models. Experiments on CA‑MER, DFEW, and EMER benchmarks show that CASE significantly boosts accuracy, notably raising Qwen3‑VL‑8B’s performance from 46.80% to 59.13%.
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
The paper investigates whether large language models can extend their agentic capabilities to goal pursuit in open-ended multi-turn dialogue. It introduces Tool-Mediated Interaction (TMI), a training-free protocol that frames dialogue actions as tool calls and responses as tool results, preserving a continuous reasoning–action–observation loop. Across social interaction, emotional support, persuasion, and price negotiation tasks, TMI improves goal attainment, preference, donation amounts, and negotiation margins while reducing reasoning tokens and cross-turn phrase reuse.
arXiv:2603. 06194v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due to sparse rewards and poor per-turn credit assignment.
The paper introduces the Affective Flow Language Model (AFlow), which treats multi‑turn emotional support conversations as an evolving affective utility flow along dialogue trajectories. AFlow searches diverse support paths, estimates utilities of intermediate states, and employs Affective Flow Preference Optimization (AFPO) to propagate downstream preference signals to earlier states, enabling consistent strategy transitions. Experiments on ExTES and ESConv demonstrate improved strategy alignment, response diversity, and generation quality across various model settings.
arXiv:2508. 09521v3 Announce Type: replace-cross Abstract: Emotional support conversations require more than fluent responses.
VISTA (Value-Informed Semantic Trust Arbitration) is a learned seven-field appraisal interface that conditions modality arbitration on concerns, event relations, and expression conditions while retaining a joint-evidence residual. It uses a log-odds decomposition to separate emotion expectation from cue diagnosticity, allowing appraisal to change how evidence is interpreted. With a shared Qwen2.5-Omni-7B backbone, VISTA achieves 64.5% conflict accuracy on CA-MER, improving on modality gating by 2.5 percentage points on conflict and 0.2 on consistency, and a frozen-backbone probe reaches 0.600 macro CCC for appraisal readout versus 0.505 for emotion-only fine-tuning.
arXiv:2606. 11379v1 Announce Type: new Abstract: Pre-mediation, the preparatory phase preceding direct human negotiation, plays a critical role in achieving mutually beneficial agreements, yet is often omitted due to cost, time, and limited access to trained mediators.
arXiv:2607. 21013v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description.