Related papers: Hound: Relation-First Knowledge Graphs for Complex…

While Large Language Model (LLM) agents show promise in automated trading, they still face critical limitations. Prominent multi-agent frameworks often suffer from inefficiency, produce inconsistent signals, and lack the end-to-end…

Inductive link prediction -- where entities during training and inference stages can be different -- has been shown to be promising for completing continuously evolving knowledge graphs. Existing models of inductive reasoning mainly focus…

Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus…

Large language models (LLMs) struggle with the factual error during inference due to the lack of sufficient training data and the most updated knowledge, leading to the hallucination problem. Retrieval-Augmented Generation (RAG) has gained…

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent…

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 violate logical or evidential constraints, allowing…

Large Language Models (LLMs) have revolutionized natural language processing, yet they struggle with inconsistent reasoning, particularly in novel domains and complex logical sequences. This research introduces Proof of Thought, a framework…

Many real world systems need to operate on heterogeneous information networks that consist of numerous interacting components of different types. Examples include systems that perform data analysis on biological information networks; social…

Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching. Various graph convolutional…

Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two…

While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited. In this paper, we propose a group-aware relational…

Language model agents reason from scratch on every query, discarding their chain of thought after each run. The result is lower accuracy and high run-to-run variance. We introduce reasoning graphs, which persist the per-evidence chain of…

Personalizing language models by effectively incorporating user interaction history remains a central challenge in the development of adaptive AI systems. While large language models (LLMs), combined with Retrieval-Augmented Generation…

Drug discovery frequently loses momentum when data, expertise, and tools are scattered, slowing design cycles. To shorten this loop we built a hierarchical, tool using agent framework that automates molecular optimisation. A Principal…

Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm…

Hallucination is a key roadblock for applications of Large Language Models (LLMs), particularly for enterprise applications that are sensitive to information accuracy. To address this issue, two general approaches have been explored:…

Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While…

Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation,…