6 papers
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
An Lanji, Dawei Liu, Jin Li +3
Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stat…
Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
Haoran Xu
LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFL…
Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument Decides
Haoran Xu, Lei Zhang, Iadh Ounis +1
Can a committee of LLM agents reach agreement that is certifiable at the level of meaning, not only at the level of a label? We build a protocol to find out. H-CSC emits one of thr…
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
Yihao Wang, Haoran Xu, Renjie Gu +10
The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, ex…
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Liliang Ren, Congcong Chen, Haoran Xu +11
Recent advances in language modeling have demonstrated the effectiveness of State Space Models (SSMs) for efficient sequence modeling. While hybrid architectures such as Samba and…
Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math
Haoran Xu, Baolin Peng, Hany Awadalla +11
Chain-of-Thought (CoT) significantly enhances formal reasoning capabilities in Large Language Models (LLMs) by training them to explicitly generate intermediate reasoning steps. Wh…