8 papers
Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints
Yutao Xie, Jingbo Yang, Guanyu Yao +3
Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking failures that arise under d…
Learning from Research: Toward Lifelong Agent Harness Evolution
Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3
Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness, the soft…
Persistent Context Graphs for Efficient Memory Compaction in LLM Agents
Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +6
As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compaction essential for staying w…
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3
Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and a…
CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems
Jingbo Yang, Guanyu Yao, Bairu Hou +5
As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operationa…
Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
Jingbo Yang, Bairu Hou, Wei Wei +2
Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable…
WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
Jingbo Yang, Bairu Hou, Wei Wei +2
Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that re…
KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
Jingbo Yang, Bairu Hou, Wei Wei +2
We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context,…