10 papers
VLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs
Borui Xu, Han Chen, Bingsheng He +3
Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in observati…
MemDerive: A Diagnostic Benchmark for Agent Memory over Evolving Data
Sen Gao, Yongan Li, Han Chen +5
Long-running agents rely on memory of their past interactions for task state, such as what has been completed and which conditions still hold. Such state is usually a derived state…
Communication-Efficient Verifiable Attention for LLM Inference
Ziqun Chen, Ming Wu, Michael Heinrich +4
Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TS…
Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
Xiang Liu, Sa Song, Zhaowei Zhang +6
Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches s…
SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
Kean Shi, Zihang Li, Tianyi Ma +13
Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browse…
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
Xinbo Xu, Ruihan Yang, Haiyang Shen +13
Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing…
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Han Chen, Zining Zhang, Wenqi Pei +6
Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial…
Inference-time Alignment via Sparse Junction Steering
Runyi Hu, Jie Zhang, Shiqian Zhao +7
Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributio…
DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster
Ji Qi, WenPeng Zhu, Li Li +6
The distributed training of foundation models, particularly large language models (LLMs), demands a high level of communication. Consequently, it is highly dependent on a centraliz…
Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
Xingshuo Han, Xuanye Zhang, Xiang Lan +7
By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Fed…