Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents

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.

Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation. However, emotion management is interactive: a good model should not only recognize a user's emotion, but also improve the user's emotional and relational state over several turns. We introduce EIBench, a simulator-based benchmark for interactive emotion management. EIBench contains 2,222 scenarios, with 2,009 for training and 213 for held-out testing. The scenarios are organized by a 2x2 taxonomy covering Support, Defense, Repair, and Charm, which together capture different forms of support, boundary maintenance, trust repair, and rapport building. In each scenario, an LLM simulator plays the user, updates an emotion-relation state after each turn, and maps the final state to an anchor-based score. This design makes EIBench both an evaluation benchmark and a training environment: the final state gives the outcome reward, while the per-turn state updates provide dense feedback for RL. We evaluate 15 open- and closed-source LLMs. Current models perform well on support and rapport-building scenes, but struggle with boundary maintenance under user pressure. To improve the EI ability of LLMs, we propose Centered Turn-Credit GRPO (CTC-GRPO), a GRPO extension that reuses the simulator's per-turn state updates as dense turn-level feedback while preserving the final outcome reward. CTC-GRPO improves Qwen3-8B from -22.4 to +22.4 on EIBench and also improves on out-of-distribution evaluations including SAGE (+12.4) and EQBench3 (+20.9%). Our results show that simulator-tracked user states can support both evaluation and training for multi-turn emotion management.

Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective. First, the binary verifier conflates format with content, so the reward signal cannot tell a wrong answer apart from a misformatted one. Second, the training distribution covers only a thin slice of the real-world prompts that the model might meet at deployment, so policies that perform well on the training distribution can behave differently under unseen prompts during test. Both failures call for a robust post-training method that helps the policy cover a broader distribution of semantically equivalent prompts, and we identify two measures that help achieve this objective: separating format from semantics in the reward, and applying policy invariance across perturbed prompts with equivalent semantics. We therefore propose Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer based on an embedding-space adversary. Under stress testing, PIRL's average accuracy on benchmarks drops by only $\le 1\%$, where GRPO drops ~3%. On dynamic evaluation, PIRL also achieves the smallest performance drop.