works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…