5 papers
ANet Patu-1: The Value of Connection in the Agent Network
Mu Yuan, Jinke Song, Zhaomeng Zhou +1
The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as (Sarnoff), fully-connected meshes as (Met…
Nice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability
Zhaomeng Zhou, Lan Zhang, Junyang Wang +6
Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by compressing re…
IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
Zhaomeng Zhou, Lan Zhang, Junyang Wang +3
Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap…
VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
Junda Lin, Zhaomeng Zhou, Zhi Zheng +4
LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback…
Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
Jiawei Cao, Jie Ouyang, Zhaomeng Zhou +4
Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adh…