GitHub

Evaluating Large Language Models using LLM-as-a-Judge

Evaluating large language models (LLM) is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, strong LLMs are used as ...
IEEE

The Crossroads of LLM and Traffic Control: A Study on Large Language Models in Adaptive Traffic Signal Control

Abstract: Recent advancements in Large Language Models (LLMs) have ushered in opportunities to craft agents that exhibit human-like cognitive abilities, notably reasoning and planning. Leveraging the ...
IEEE

A Survey of LLM-based Agents: Theories, Technologies, Applications and Suggestions

Abstract: AI Agent has presented potential towards Artificial General Intelligence (AGI), which is expected to autonomously perceive the environments, make decisions and take actions. However, most of ...
GitHub

[BUG] TensorRT-LLM NIXL Wrapper Symbol Incompatibility with NIXL 0.6.0+ API Changes

TensorRT-LLM v1.1.0rc5 NIXL wrapper is incompatible with NIXL 0.6.0+ due to a fundamental breaking API change in the nixlDescList constructor. This causes undefined symbol errors at runtime, ...