4 papers · 1 filter
Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents
Wenhao Yuan, Chenchen Lin, Jian Chen +3
Long-horizon multimodal agents rely on specialized capabilities for perception, retrieval, reasoning, verification, and execution. Existing designs typically activate a fixed capab…
Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
Chenchen Lin, Wenhao Yuan, Xuehe Wang +1
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence…
Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations
Wenhao Yuan, Chenchen Lin, Jian Chen +3
In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial comp…
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
Wenhao Yuan, Chenchen Lin, Jian Chen +3
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still…