Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908456578973696 |
|---|---|
| author | Soni, Jubin Abhishek Anand, Amit Pandey, Rajesh Kumar Soni, Aniket Abhishek |
| author_facet | Soni, Jubin Abhishek Anand, Amit Pandey, Rajesh Kumar Soni, Aniket Abhishek |
| contents | Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn interactions with fixed toolsets, making them ill-suited for dynamic domains such as healthcare and smart homes, where user intent, available tools, and contextual factors evolve over time. We present Dynamic Context Tuning (DCT), a lightweight framework that extends RAG to support multi-turn dialogue and evolving tool environments without requiring retraining. DCT integrates an attention-based context cache to track relevant past information, LoRA-based retrieval to dynamically select domain-specific tools, and efficient context compression to maintain inputs within LLM context limits. Experiments on both synthetic and real-world benchmarks show that DCT improves plan accuracy by 14% and reduces hallucinations by 37%, while matching GPT-4 performance at significantly lower cost. Furthermore, DCT generalizes to previously unseen tools, enabling scalable and adaptable AI assistants across a wide range of dynamic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation Soni, Jubin Abhishek Anand, Amit Pandey, Rajesh Kumar Soni, Aniket Abhishek Computation and Language Artificial Intelligence Human-Computer Interaction Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn interactions with fixed toolsets, making them ill-suited for dynamic domains such as healthcare and smart homes, where user intent, available tools, and contextual factors evolve over time. We present Dynamic Context Tuning (DCT), a lightweight framework that extends RAG to support multi-turn dialogue and evolving tool environments without requiring retraining. DCT integrates an attention-based context cache to track relevant past information, LoRA-based retrieval to dynamically select domain-specific tools, and efficient context compression to maintain inputs within LLM context limits. Experiments on both synthetic and real-world benchmarks show that DCT improves plan accuracy by 14% and reduces hallucinations by 37%, while matching GPT-4 performance at significantly lower cost. Furthermore, DCT generalizes to previously unseen tools, enabling scalable and adaptable AI assistants across a wide range of dynamic environments. |
| title | Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2506.11092 |