Related papers: GraphTracer: Graph-Guided Failure Tracing in LLM A…

ChatGPT said: Text-attributed graphs, where nodes and edges contain rich textual information, are widely used across diverse domains. A central challenge in this setting is question answering, which requires jointly leveraging unstructured…

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple…

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Agentic systems augment large language models with external tools and iterative decision making, enabling complex tasks such as deep research, function calling, and coding. However, their long and intricate execution traces make failure…

Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not…

LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM…

Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…

Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM…

Large-scale telecom and datacenter infrastructures rely on multi-layered service and resource models, where failures propagate across physical and logical components and affect multiple customers. Traditional approaches to root cause…

Despite recent progress, Graphic User Interface (GUI) agents powered by Large Language Models (LLMs) struggle with complex mobile tasks due to limited app-specific knowledge. While UI Transition Graphs (UTGs) offer structured navigation…

Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large knowledge graphs. Existing approaches often rely on monolithic…

Scaling adaptive traffic-signal control involves dealing with combinatorial state and action spaces. Multi-agent reinforcement learning attempts to address this challenge by distributing control to specialized agents. However,…

Multi-Agent Reinforcement Learning (MARL) is increasingly deployed in safety-critical domains, yet methods for interpretable failure detection and attribution remain underdeveloped. We introduce a two-stage gradient-based framework that…

LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from…

As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing their capabilities in increasingly complex and diverse tasks.…

Current AI-assisted innovation systems typically apply a single ideation methodology (such as TRIZ or Design Thinking) using sequential prompt-based workflows that do not preserve intermediate reasoning structure. As a result, insights…

With the rise of large language models (LLMs), there has been growing interest in Graph Foundation Models (GFMs) for graph-based tasks. By leveraging LLMs as predictors, GFMs have demonstrated impressive generalizability across various…

We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities for generating…

Retrieval-augmented generation (RAG) is a powerful paradigm for improving large language models (LLMs) on knowledge-intensive question answering. Graph-based RAG (GraphRAG) leverages entity-relation graphs to support multi-hop reasoning,…

Real-world data is represented in both structured (e.g., graph connections) and unstructured (e.g., textual, visual information) formats, encompassing complex relationships that include explicit links (such as social connections and user…