8 papers
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
Xiaochong Jiang, Shiqi Yang, Ziwei Li +3
Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This…
MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
Srinivas Sridharan, Theodor-Adrian Badea, Andy Balogh +26
The fast pace of artificial intelligence~(AI) innovation demands an agile methodology for observation, reproduction and optimization of distributed machine learning~(ML) workload b…
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
Linfeng Fan, Ziwei Li, Yuan Tian +3
Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity o…
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
Linfeng Fan, Yuan Tian, Ziwei Li +1
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existi…
MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems
Haobo Zhang, Xutao Mao, Guangyuan Dong +5
Memory-backed agents need provenance that can survive leaked or migrated snapshots, where logs, visible outputs, and trusted metadata may be absent. We propose MemMark, a state-evo…
Sell More, Play Less: Benchmarking LLM Realistic Selling Skill
Xuanbo Su, Wenhao Hu, Le Zhan +8
Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language models (LLMs). Yet existing dial…