From the 1 of 5 linked papers with an AI index.
5 papers
LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
Enjun Du, Hange Zhou, Chenxu Du +4
The paper introduces LedgerMind, a framework that records and constrains the evidence used by multimodal agents during visual question answering, ensuring that each reasoning step…
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
Yuhang He, Haodong Wu, Siyi Liu +7
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment…
GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs
Enjun Du, Siyi Liu, Yongqi Zhang
Knowledge graph reasoning in the fully-inductive setting, where both entities and relations at test time are unseen during training, remains an open challenge. In this work, we int…
StructSynth: Leveraging LLMs for Structure-Aware Tabular Data Synthesis in Low-Data Regimes
Siyi Liu, Yujia Zheng, Yongqi Zhang
The application of machine learning on tabular data in specialized domains is severely limited by data scarcity. While generative models offer a solution, traditional methods falte…
Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning
Enjun Du, Siyi Liu, Yongqi Zhang
Knowledge Graph (KG) reasoning, which aims to infer new facts from structured knowledge repositories, plays a vital role in Natural Language Processing (NLP) systems. Its effective…