4 papers
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jundong Xu, Qingchuan Li, Jiaying Wu +11
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deploymen…
DVM: Towards Controllable LLM Agents in Social Deduction Games
Zheng Zhang, Yihuai Lan, Yangsen Chen +3
Large Language Models (LLMs) have advanced the capability of game agents in social deduction games (SDGs). These games rely heavily on conversation-driven interactions and require…
All in an Aggregated Image for In-Image Learning
Lei Wang, Wanyu Xu, Zhiqiang Hu +5
This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (IL) that combines demonstration examples, visual cues, and chain-of-thought reasoning…
PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models
Jinyi Li, Yihuai Lan, Lei Wang +1
Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interf…