ID-TAP: dueling-bandit framework personalizes LLM agents from binary feedback in a limited interaction budget
Jie Mao · hf · 2026-10-24
Researchers from CUHK-Shenzhen, U. Copenhagen, CityU HK and ECNU present ID-TAP (arXiv, Oct 2026), tackling test-time personalization: adapting LLM agents to query-dependent user preferences via binary comparisons between candidate responses as the online signal.
ID-TAP is an IDS-inspired neural dueling-bandit framework for large discrete persona spaces, combining a query-conditioned neural utility model with a lightweight Bradley–Terry explorer, and transferring comparison evidence across related queries through similarity-weighted warm starts. Code: github.com/s1412/ID-TAP.
More from coding & agent
- Kaigen AI-native game engine scales linearly to 40k players, opens v0.7.0 beta — gdechichi · 2026-10-24
- Banks are blocking shared-credential AI agents; a new map charts the protocols that could fix agent auth — csuwildcat · 2026-10-24
- 20-year AI veteran curates 19 free open-source repos for building AI agents — MaryamMiradi · 2026-10-24
- Microsoft retires Fabric data agent custom tool in Foundry, pivots to Fabric IQ — adnan_hashmi · 2026-10-24
- A 2-person AI team built its own video tool and dropped Zoom entirely — danshipper · 2026-10-24
- Agent posting safety: publish, fetch as a stranger, then assert on what's actually there — petrusenko_max · 2026-10-24