# Optimizing Large Language Models for Dynamic Constraints through Human-in-the-Loop Discriminators

arXiv: https://arxiv.org/abs/2410.15163 · HTML: https://mlsanity.com/paper/2410.15163/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 19 Oct 2024.

## Builds on (most cited first, 12 of 12)

- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [Data-efficient Fine-tuning for LLM-based Recommendation](https://mlsanity.com/paper/2401.17197/) (2024)
- [WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration](https://mlsanity.com/paper/2408.15978/) (2024)
- [A Survey on Self-play Methods in Reinforcement Learning](https://mlsanity.com/paper/2408.01072/) (2024)
- [TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization](https://mlsanity.com/paper/2212.09254/) (2022)

## Built on by (most cited first, 1 of 1)

- [Decoupled Travel Planning with Behavior Forest](https://mlsanity.com/paper/2604.21354/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have recently demonstrated impressive capabilities across various real-world applications. However, due to the current text-in-text-out paradigm, it remains challenging for LLMs to handle dynamic and complex application constraints, let alone devise general solutions that meet predefined system goals. Current common practices like model finetuning and reflection-based reasoning often address these issues case-by-case, limiting their generalizability. To address this issue, we propose a flexible framework that enables LLMs to interact with system interfaces, summarize constraint concepts, and continually optimize performance metrics by collaborating with human experts. As a case in point, we initialized a travel planner agent by establishing constraints from evaluation interfaces. Then, we employed both LLM-based and human discriminators to identify critical cases and continuously improve agent performance until the desired outcomes were achieved. After just one iteration, our framework achieved a 7.78% pass rate with the human discriminator (a 40.2% improvement over baseline) and a 6.11% pass rate with the LLM-based discriminator. Given the adaptability of our proposal, we believe this framework can be applied to a wide range of constraint-based applications and lay a solid foundation for model finetuning with performance-sensitive data samples.