Input Conditioned Graph Generation for Language Agents
Abstract: Recent progress in the areas of Large Language Models (LLMs) and Language Agents has demonstrated significant promise for various future applications across multiple disciplines. While traditional approaches to language agents often rely on fixed, handcrafted designs, our research aims to develop agents that are both learnable and dynamic.
In our method, we use an existing framework that abstracts language agents as graphs. Within this graph framework, we aim to learn a model that can generate edges for every given input to the language agent. This allows us to generate edges that represent the flow of communication within the graph based on the given input, thereby adjusting the internal communication of a language agent. We learn to generate these edges using a pretrained LLM that is fine-tuned with reinforcement learning. This LLM can be fine-tuned on several datasets simultaneously, and we hypothesize that the model learns to adapt to these different domains during training, achieving good overall performance when encountering data from different domains during deployment. We demonstrate that our approach surpasses the previous static approach by nearly 6% accuracy on a combined dataset of MMLU and CMMLU, and by more than 10% when trained with a sparsity-inducing loss. It also shows superior performance in additional experiments conducted with the MMLU and Mini Crossword Puzzles datasets.
Paper Type: Long
Research Area: Machine Learning for NLP
Research Area Keywords: Language Agents
Contribution Types: NLP engineering experiment, Reproduction study
Languages Studied: English,Chinese
Submission Number: 484
Loading