Tag
This paper proposes a novel contextual bandit algorithm that explicitly models reward decay for progressive content refinement in LLMs, using EM to estimate arm-specific and decay parameters. Experiments on Sentiment Reversal and GSM8K show significant gains over strong baselines.
The paper proposes a Predict-then-Correct (PtC) framework using a few-shot continuous contextual bandit to adaptively correct base ML forecasts in retail demand forecasting, achieving significant improvements in error metrics and inventory costs over baselines.
This paper identifies that current LLM agents fail to systematically explore their peers, leading to poor coordination, and introduces MACE, a lightweight framework using contextual bandits for effective peer selection.
This paper presents VDSS, a human-in-the-loop multi-agent framework for ventilator decision support that uses contextual bandit preference learning to adapt to clinician-specific tuning styles, with retrospective ICU trajectory replays showing improved recommendation acceptability and reduced interaction rounds.
Announces two open-source Rust projects: Lycan (a graph execution language for contextual bandits) and Syntra (a self-hosted Docker appliance for serving Lycan capsules). The author dogfoods them on a live AI trading product, discovering that data pipeline bugs, not algorithm issues, dominated the adaptation work.
This paper introduces LQM-ContextRoute, a contextual bandit router for selecting between functionally equivalent tool providers in LLM agents, balancing latency and answer quality. It outperforms baselines on web-search and retriever benchmarks.