Abstract:Wide applications of LLM-based agents require strong alignment with human social values. However, current works still exhibit deficiencies in self-cognition and dilemma decision, as well as self-emotions. To remedy this, we propose a novel value-based framework that employs GraphRAG to convert principles into value-based instructions and steer the agent to behave as expected by retrieving the suitable instruction upon a specific conversation context. To evaluate the ratio of expected behaviors, we define the expected behaviors from two famous theories, Maslow's Hierarchy of Needs and Plutchik's Wheel of Emotion. By experimenting with our method on the benchmark of DAILYDILEMMAS, our method exhibits significant performance gains compared to prompt-based baselines, including ECoT, Plan-and-Solve, and Metacognitive prompting. Our method provides a basis for the emergence of self-emotion in AI systems.
| Comments: | Accepted by CogSci 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY) |
| Cite as: | arXiv:2605.14034 [cs.AI] |
| (or arXiv:2605.14034v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14034 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luo Ji [view email]
[v1]
Wed, 13 May 2026 18:50:22 UTC (950 KB)