9 papers
SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
Ning Yang, Siqi Li, Miaoxin Shen +4
Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning. Strategic Forgetting for Ag…
Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations
Devika Prasad, Luke Gerschwitz, Tong Li +5
Prompt engineering is crucial for effective interaction with generative artificial intelligence systems, yet existing optimisation methods often operate over an unstructured and va…
AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor
Shu Yang, Jingyu Hu, Tong Li +3
We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. Au…
Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
Chuanrui Hu, Tong Li, Xingze Gao +8
Long-term conversational memory in practical LLM applications is inherently collaborative: information is produced by multiple participants, scattered across groups and channels, r…
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
Chuanrui Hu, Xingze Gao, Zuyi Zhou +8
Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extend…
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
Mo Yu, Tsz Ting Chung, Chulun Zhou +8
We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character's prequel story is consistent with the canonical nar…