Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support
This addresses the need for more adaptive and efficient decision support in AI systems, though it appears incremental as it builds on existing LLM and MCTS methods with task-aware routing.
The paper tackles the problem of LLMs lacking specialization awareness in decision-making by proposing TALC, a task-adaptive framework that uses a council of LLMs with MCTS for dynamic expert selection, resulting in superior task success rates and improved search efficiency on benchmarks like WebShop, HumanEval, and Game of 24.
Large language models (LLMs) have shown strong capabilities across diverse decision-making tasks. However, existing approaches often overlook the specialization differences among available models, treating all LLMs as uniformly applicable regardless of task characteristics. This limits their ability to adapt to varying reasoning demands and task complexities. In this work, we propose Task-Aware LLM Council (TALC), a task-adaptive decision framework that integrates a council of LLMs with Monte Carlo Tree Search (MCTS) to enable dynamic expert selection and efficient multi-step planning. Each LLM is equipped with a structured success memory profile derived from prior task trajectories, enabling semantic matching between current reasoning context and past successes. At each decision point, TALC routes control to the most contextually appropriate model and estimates node value using a dual-signal mechanism that fuses model-based evaluations with historical utility scores. These signals are adaptively weighted based on intra-node variance and used to guide MCTS selection, allowing the system to balance exploration depth with planning confidence. Experiments on WebShop, HumanEval, and the Game of 24 demonstrate that TALC achieves superior task success rates and improved search efficiency compared to strong baselines, validating the benefits of specialization-aware routing and adaptive planning.