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: LLM Judges Under-use the Non-Directional Verdicts Their Contract Authorizes
Haoran Xu
Evidence-grounded fact verification increasingly uses LLM judges to turn evidence into terminal verdicts. Many task contracts deliberately include non-directional verdicts - Confli…
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…