5 papers
TRACER: Trajectory-Aware Tool Retrieval for LLM Agents
Tanish Kher, Sarvesh DK, Abedelkadir Asi +2
Modern agents select tools from registries, but exposing entire registries incurs high token costs and can impair selection as they grow. We present TRACER, a retrieval front-end t…
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Dachuan Shi, Abedelkadir Asi, Keying Li +4
Recent work shows that, beyond discrete reasoning through explicit chain-of-thought steps, which are limited by the boundaries of natural languages, large language models (LLMs) ca…
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Zefan Cai, Wen Xiao, Hanshi Sun +11
Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohib…
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Yu Fu, Zefan Cai, Abedelkadir Asi +3
Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior…
An End-to-End Dialogue Summarization System for Sales Calls
Abedelkadir Asi, Song Wang, Roy Eisenstadt +4
Summarizing sales calls is a routine task performed manually by salespeople. We present a production system which combines generative models fine-tuned for customer-agent setting,…