Search papers, labs, and topics across Lattice.
The paper introduces Context-Agent, a framework that represents multi-turn dialogues as dynamic tree structures to better capture the non-linear nature of conversations. This approach allows LLMs to maintain and navigate multiple dialogue branches, improving context utilization and coherence. Experiments on the new Non-linear Task Multi-turn Dialogue (NTM) benchmark show that Context-Agent improves task completion rates and token efficiency across various LLMs.
LLMs can handle complex, multi-turn conversations far more effectively by ditching the flat context window for a dynamic discourse tree.
Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat, linear sequence is misaligned with the intrinsically hierarchical and branching structure of natural discourse, leading to inefficient context utilization and a loss of coherence during extended interactions involving topic shifts or instruction refinements. To address this limitation, we introduce Context-Agent, a novel framework that models multi-turn dialogue history as a dynamic tree structure. This approach mirrors the inherent non-linearity of conversation, enabling the model to maintain and navigate multiple dialogue branches corresponding to different topics. Furthermore, to facilitate robust evaluation, we introduce the Non-linear Task Multi-turn Dialogue (NTM) benchmark, specifically designed to assess model performance in long-horizon, non-linear scenarios. Our experiments demonstrate that Context-Agent enhances task completion rates and improves token efficiency across various LLMs, underscoring the value of structured context management for complex, dynamic dialogues. The dataset and code is available at GitHub.
