4 papers
The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms
Dahlia Shehata, Ming Li
As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collaboration mirrors the "Wisdom o…
Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols
Dahlia Shehata, Ming Li
As LLM agents transition to autonomous digital coworkers, maintaining deterministic goal-directedness in non-linear multi-turn conversations emerged as an architectural bottleneck.…
Revisable by Design: A Theory of Streaming LLM Agent Execution
Zhiyuan Zhai, Ming Li, Xin Wang
Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon complet…
Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
Tianyi Xiong, Yi Ge, Ming Li +13
Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences.…