Related papers: HiRA: A Hierarchical Reasoning Framework for Decou…

To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful…

Low-Rank Adaptation (LoRA) layers have emerged as a promising approach for efficient model fine-tuning, but their capabilities and limitations have not been fully explored. This paper: 1) Investigates the fundamental question of whether…

Retrieval-Augmented Generation (RAG) has proven effective for knowledge synthesis, yet it encounters significant challenges in practical scenarios where data is inherently discrete and fragmented. In most environments, information is…

Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic…

Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both…

We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our…

Retrieval-augmented generation (RAG) has demonstrated strong performance in single-hop question answering (QA) by integrating external knowledge into large language models (LLMs). However, its effectiveness remains limited in multi-hop QA,…

Retrieval-Augmented Generation (RAG) plays a crucial role in grounding Large Language Models by leveraging external knowledge, whereas the effectiveness is often compromised by the retrieval of contextually flawed or incomplete information.…

Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental results. However, existing approaches still use fixed sequential agent pipelines with weak…

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation…

Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing studies that mainly focus on unstructured web content, a…

Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource…

Leveraging the autonomous decision-making capabilities of large language models (LLMs) has demonstrated superior performance in reasoning tasks. However, despite the success of iterative or agentic retrieval-augmented generation (RAG)…

Recent advances in visual reasoning (VR), particularly with the aid of Large Vision-Language Models (VLMs), show promise but require access to large-scale datasets and face challenges such as high computational costs and limited…

Professional domain knowledge underpins human civilization, serving as both the basis for industry entry and the core of complex decision-making and problem-solving. However, existing large language models often suffer from opaque inference…

Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate…

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph…

Recent advancements have significantly enhanced the performance of large language models (LLMs) in tackling complex reasoning tasks, achieving notable success in domains like mathematical and logical reasoning. However, these methods…

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from…

Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in…