{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rlver-reinforcement-learning-with-verifiable","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","arxiv_id":"2507.03112","date":"2025-07-03","proceeding":null,"authors":["Peisong Wang","Ruotian Ma","Bang Zhang","Xingyu Chen","Zhiwei He","Kang Luo","Qingsong Lv","Qingxuan Jiang","Zheng Xie","Shanyi Wang","Yuan Li","Fanghua Ye","Jian Li","Yifan Yang","Zhaopeng Tu","Xiaolong Li"],"abstract":"Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other domains, its application to dialogue-especially for emotional intelligence-remains underexplored. In this work, we introduce RLVER, the first end-to-end reinforcement learning framework that leverages verifiable emotion rewards from simulated users to cultivate higher-order empathetic abilities in LLMs. Within this framework, self-consistent affective simulated users engage in dialogue rollouts and produce deterministic emotion scores during conversations, serving as reward signals to guide the LLM's learning. Fine-tuning publicly available Qwen2.5-7B-Instruct model with PPO boosts its Sentient-Benchmark score from 13.3 to 79.2 while largely preserving mathematical and coding competence. Extensive experiments reveal that: (i) RLVER consistently improves multiple dialogue capabilities; (ii) Thinking and non-thinking models show distinct trends--thinking models excel in empathy and insight, while non-thinking models favor action; (iii) GRPO often yields stable gains, while PPO can push certain capabilities to a higher ceiling; (iv) More challenging environments are not always better-moderate ones can yield stronger outcomes. Our results show that RLVER is a practical route toward emotionally intelligent and broadly capable language agents.","url_abs":"https://arxiv.org/abs/2507.03112v1","url_pdf":"https://arxiv.org/pdf/2507.03112v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rlver-reinforcement-learning-with-verifiable","repo_url":"https://github.com/tencent/digitalhuman","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"emotional-intelligence","task_name":"Emotional Intelligence"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2507.03112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.03112"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tencent/digitalhuman","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"fcb1082d2b5dfb78","entry":"compute_attention_mask","repo":"tencent/digitalhuman","repo_kind":"official","path":"RLVER/code/tests/e2e/envs/digit_completion/task.py","file_url":"https://github.com/tencent/digitalhuman/blob/HEAD/RLVER/code/tests/e2e/envs/digit_completion/task.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fcb1082d2b5dfb78"}},{"code_sha256_prefix":"518164bb357253e8","entry":"compute_position_id_with_mask","repo":"tencent/digitalhuman","repo_kind":"official","path":"RLVER/code/tests/e2e/envs/digit_completion/task.py","file_url":"https://github.com/tencent/digitalhuman/blob/HEAD/RLVER/code/tests/e2e/envs/digit_completion/task.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"518164bb357253e8"}},{"code_sha256_prefix":"769ee29d4ca23c1e","entry":"generate_ground_truth_response","repo":"tencent/digitalhuman","repo_kind":"official","path":"RLVER/code/tests/e2e/envs/digit_completion/task.py","file_url":"https://github.com/tencent/digitalhuman/blob/HEAD/RLVER/code/tests/e2e/envs/digit_completion/task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"769ee29d4ca23c1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}