2026 NeurIPS
Test-Time Risk Adaptation with Mixture of Agents
A test-time risk-adaptation method that composes source agents according to deployment-time risk specifications.
Research
03 / Research direction
LLMs for Constrained Decision Systems
Fine-tuning and inference-time methods for language models that propose technical actions under constraints.
The goal is not only better text generation, but more reliable decisions when language models interact with structured domains.
Papers
Related work in this direction
3 papers connected to this topic.
2026 PESGM
Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid
A fine-tuning framework for language models that generate corrective power-grid actions while balancing cost and reliability.
2025 ICML
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
An inference-time alignment method that treats acceptable behavior through satisficing rather than single-objective maximization.