English
Related papers

Related papers: CodeCompass: Navigating the Navigation Paradox in …

200 papers

In our research, we investigate the challenges that software engineers face during program comprehension, particularly when debugging unfamiliar codebases. We propose a novel tool, CodeCompass, to address these issues. Our study highlights…

Software Engineering · Computer Science 2024-05-13 Ekansh Agrawal , Omair Alam , Chetan Goenka , Medha Iyer , Isabela Moise , Ashish Pandian , Bren Paul

Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to…

Information Retrieval · Computer Science 2026-03-24 Xuanwang Zhang , Yuteng Han , Jinnan Qi , Mulong Xie , Zhen Wu , Xinyu Dai

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Software Engineering · Computer Science 2026-04-06 Tural Mehtiyev , Wesley Assunção

When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…

Machine Learning · Computer Science 2022-06-24 Khanh Nguyen , Yonatan Bisk , Hal Daumé

We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant…

Artificial Intelligence · Computer Science 2026-02-17 Shifat E. Arman , Syed Nazmus Sakib , Tapodhir Karmakar Taton , Nafiul Haque , Shahrear Bin Amin

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

Artificial Intelligence · Computer Science 2025-10-30 Jiaqi Wu , Qinlao Zhao , Zefeng Chen , Kai Qin , Yifei Zhao , Xueqian Wang , Yuhang Yao

Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce The Amazing Agent Race (AAR), a benchmark featuring directed…

Artificial Intelligence · Computer Science 2026-04-20 Zae Myung Kim , Dongseok Lee , Jaehyung Kim , Vipul Raheja , Dongyeop Kang

Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code…

Software Engineering · Computer Science 2025-10-01 Esakkivel Esakkiraja , Denis Akhiyarov , Aditya Shanmugham , Chitra Ganapathy

Large Language Model agents increasingly operate external systems through programmatic interfaces, yet practitioners lack empirical guidance on how to structure the context these agents consume. Using SQL generation as a proxy for…

Computation and Language · Computer Science 2026-02-13 Damon McMillan

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Artificial Intelligence · Computer Science 2025-10-13 Guangya Wan , Mingyang Ling , Xiaoqi Ren , Rujun Han , Sheng Li , Zizhao Zhang

Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must mirror this capability. We introduce COMPASS, a benchmark…

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and…

This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We…

Information Retrieval · Computer Science 2026-04-17 Koushik Chakraborty , Koyel Guha

AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…

Software Engineering · Computer Science 2026-04-16 Ruoqi Jin

Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool composition: an agent can…

Cryptography and Security · Computer Science 2026-05-27 Xiaochong Jiang , Shiqi Yang , Ziwei Li , Lifei Liu , Haoran Yu , Yichen Liu

The use of knowledge graphs for grounding agents in real-world Q&A applications has become increasingly common. Answering complex queries often requires multi-hop reasoning and the ability to navigate vast relational structures. Standard…

Artificial Intelligence · Computer Science 2026-04-03 Taraneh Ghandi , Hamidreza Mahyar , Shachar Klaiman

Deploying autonomous agents in real world environments is challenging, particularly for navigation, where systems must adapt to situations they have not encountered before. Traditional learning approaches require substantial amounts of…

Robotics · Computer Science 2026-03-10 Quang-Anh N. D. , Duc Pham , Minh-Anh Nguyen , Tung Doan , Tuan Dang

We develop a language-guided navigation task set in a continuous 3D environment where agents must execute low-level actions to follow natural language navigation directions. By being situated in continuous environments, this setting lifts a…

Computer Vision and Pattern Recognition · Computer Science 2020-05-05 Jacob Krantz , Erik Wijmans , Arjun Majumdar , Dhruv Batra , Stefan Lee

Large Language Models (LLMs) offer significant promise for intelligent traffic management; however, current chain-based systems like TrafficGPT are hindered by sequential task execution, high token usage, and poor scalability, making them…

Artificial Intelligence · Computer Science 2025-07-21 Nabil Abdelaziz Ferhat Taleb , Abdolazim Rezaei , Raj Atulkumar Patel , Mehdi Sookhak

Although Vehicle Routing Problems (VRP) are essential to many real-world systems, they remain computationally intractable at scale due to their combinatorial complexity. Traditional heuristics rely on handcrafted rules for local…

Artificial Intelligence · Computer Science 2026-05-21 Oleksandr Yakovenko , Mahdi Mostajabdaveh , Cheikh Ahmed , Abdullah Ali Sivas , Xiaorui Li , Zirui Zhou , Mao Kun
‹ Prev 1 2 3 10 Next ›