{"arxiv_id":"2608.09248","title":"Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution","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. 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. We propose Emotion2Skill, a framework that extracts LLM-internal emotion vectors and incorporates them into both skill selection and skill evolution. At each decision step, a 27-dimensional emotion state is extracted from the residual stream and mapped to a confidence-gated summary injected into the routing prompt. Beyond online selection, emotion trajectories are analyzed for abrupt internal-state shifts to pinpoint problematic skill invocations, guiding targeted SOP rewriting that replaces the coarse binary outcome signal of prior methods. On WebShop and ALFWorld, Emotion2Skill with Qwen3-8B improves over the Zero-Shot baseline by +26.9% success rate and +25.5% average success respectively, outperforming all baselines on both benchmarks with consistent gains on Qwen3-14B. Co-activation analysis further reveals semantically coherent emotion--skill pairings, confirming that the routing improvements reflect meaningful internal-state signals rather than opaque statistical correlations. These results establish LLM-internal emotion representations as an effective decision-level signal for orchestrating agent skill systems, extending their utility beyond interpretability and output steering. The code is available at https://github.com/BoHan-LIN04/Emotion2Skill.","primary_cat":"cs.AI","cross_cats":[],"submitted_at":"2026-08-10T08:09:24+00:00","latest_version":2,"source":"arxiv","source_label":"arXiv","source_url":null,"has_pdf":true,"has_source":false,"verdict":"CONDITIONAL","confidence":"MODERATE","one_line_summary":"LLM-internal emotion vectors, injected into skill-selection prompts via a confidence gate and used to localize skill rewriting, improve agent success rates on WebShop and ALFWorld over text-only baselines.","novelty_score":7.0,"correctness_risk":"medium","formal_verification":"none","upvotes":0,"downvotes":0,"pith_score":0.0,"inbound_count":1,"_links":{"html":"https://pith.science/paper/2608.09248","verdict":"/api/v1/verdicts/2608.09248"}}