paper-with-me

홈 › Papers

TweakLLM: A Routing Architecture for Dynamic Tailoring of Cached Responses

2025-07-31 · Muhammad Taha Cheema, Abeer Aamir, Khawaja Gul Muhammad, Naveed Anwar Bhatti, Ihsan Ayyub Qazi, Zafar Ayyub Qazi arxiv

Large Language Models (LLMs) process millions of queries daily, making efficient response caching a compelling optimization for reducing cost and latency. However, preserving relevance to user queries using this approach proves difficult due to the personalized nature of chatbot interactions and the limited accuracy of semantic similarity search. To address this, we present TweakLLM, a novel routing architecture that employs a lightweight LLM to dynamically adapt cached responses to incoming prompts. Through comprehensive evaluation, including user studies with side-by-side comparisons, satisfaction voting, as well as multi-agent LLM debates, we demonstrate that TweakLLM maintains response quality comparable to frontier models while significantly improving cache effectiveness. Our results across real-world datasets highlight TweakLLM as a scalable, resource-efficient caching solution for high-volume LLM deployments without compromising user experience.

📄 PDF Abstract BibTeX arXiv:2507.23674

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving

2025-12-07 · Wei-Bin Kou, Guangxu Zhu, Jingreng Lei, Chen Zhang 외 arxiv

Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, such as varying weather, traffic densitie…

Semantic SegmentationAutonomous Driving

Sub-Token Routing for KV Cache Compression

2026-04-23 · Wei Jiang, Wei Wang arxiv

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, o…

multimodal generation

D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing

2026-03-15 · Yuru Song, Qi Xin arxiv

Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a bio…

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

2026-05-26 · Syed Huma Shah arxiv

Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV reuse is now standard in serving stacks such as vLLM, and chunk-leve…

Bending beams for 6G near-field communications

2024-10-10 · Sotiris Droulias, Giorgos Stratidakis, Angeliki Alexiou

Future wireless connectivity is envisioned to accommodate functionalities far beyond broadband data transmission over point-to-point direct links, enabling novel scenarios, such as communication behind blockers and aroun…