Related papers: Deep Researcher with Sequential Plan Reflection an…
Recursive query processing has experienced a recent resurgence, as a result of its use in many modern application domains, including data integration, graph analytics, security, program analysis, networking and decision making. Due to the…
As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existing systems suffer from limited analytical depth due to reliance on abstracts and…
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…
Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes depth-recurrence due to partially fixed layer stacks, and…
High-Performance Computing (HPC) platforms enable scientific software to achieve breakthroughs in many research fields such as physics, biology, and chemistry, by employing Research Software Engineering (RSE) techniques. These include 1)…
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…
We present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make…
We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…
Recently, differentiable search methods have made major progress in reducing the computational costs of neural architecture search. However, these approaches often report lower accuracy in evaluating the searched architecture or…
The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users. Significant efforts have been made to enhance the capabilities of SR systems. These…
Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…
Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel.…
Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents to further enhance problem-solving capability. However, conventional parallel thinking faces two key challenges in this…
Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks. Among them, DeepSeek R1 has garnered significant attention for its exceptional performance and…
The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review…
Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models. Frontier deep research products score high on existing…
Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks…
We introduce DeepResearch$^{\text{Eco}}$, a novel agentic LLM-based system for automated scientific synthesis that supports recursive, depth- and breadth-controlled exploration of original research questions -- enhancing search diversity…
Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving…
We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…