English
Related papers

Related papers: The Specification Gap: Coordination Failure Under …

200 papers

We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of existing math word problems together so that the answer to the second problem depends on correctly…

Machine Learning · Computer Science 2024-10-03 Arian Hosseini , Alessandro Sordoni , Daniel Toyama , Aaron Courville , Rishabh Agarwal

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

Artificial Intelligence · Computer Science 2026-03-31 Faouzi El Yagoubi , Godwin Badu-Marfo , Ranwa Al Mallah

Online question-and-answer (Q\&A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. This paper proposed a Multi-Agent framework with environmentally reinforcement learning…

Software Engineering · Computer Science 2024-09-05 Jiapeng Yu , Yuqian Wu , Yajing Zhan , Wenhao Guo , Zhou Xu , Raymond Lee

Multi-agent coordination dilemmas expose a fundamental tension between individual optimization and collective welfare, yet characterizing such coordination requires metrics sensitive to temporal structure and collective dynamics. As a…

Multiagent Systems · Computer Science 2026-03-24 Nikolaos Al. Papadopoulos , Konstantinos Psannis

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

Artificial Intelligence · Computer Science 2026-02-04 Abdelghny Orogat , Ana Rostam , Essam Mansour

Compilers are complex, and significant effort has been expended on testing them. Techniques such as random program generation and differential testing have proved highly effective and have uncovered thousands of bugs in production…

Software Engineering · Computer Science 2025-01-03 Davide Italiano , Chris Cummins

Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understanding of why MAS fail. Addressing this question requires…

Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We study this failure mode as overcommitment control and…

Computation and Language · Computer Science 2026-05-19 Tianyi Huang , Samuel Xu , Jason Tansong Dang , Samuel Yan , Kimberley Yin

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Large Language Models (LLMs) for code generation boost productivity but frequently introduce Knowledge Conflicting Hallucinations (KCHs), subtle, semantic errors, such as non-existent API parameters, that evade linters and cause runtime…

Software Engineering · Computer Science 2026-01-28 Dipin Khati , Daniel Rodriguez-Cardenas , Paul Pantzer , Denys Poshyvanyk

Run the same LLM agent on the same task twice: do you get the same behavior? We find the answer is often no. In a study of 3,000 agent runs across three models (Llama 3.1 70B, GPT-4o, and Claude Sonnet 4.5) on HotpotQA, we observe that…

Artificial Intelligence · Computer Science 2026-02-13 Aman Mehta

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error…

Multiagent Systems · Computer Science 2026-05-21 Yong Jin Chun , Iftekhar Ahmed

Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…

Computation and Language · Computer Science 2026-02-05 Woongkyu Lee , Junhee Cho , Jungwook Choi

Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected…

Computation and Language · Computer Science 2025-05-19 Baixuan Xu , Chunyang Li , Weiqi Wang , Wei Fan , Tianshi Zheng , Haochen Shi , Tao Fan , Yangqiu Song , Qiang Yang

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Artificial Intelligence · Computer Science 2025-01-14 Amr Almorsi , Mohanned Ahmed , Walid Gomaa

An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…

Computation and Language · Computer Science 2026-05-05 Kwan Soo Shin

Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts the result it claims to measure. This failure is not isolated: learned critics, trajectory-level…

Machine Learning · Computer Science 2026-05-11 Yanjun Chen , Yirong Sun , Hanlin Wang , Jinghan Wang , Xinming Zhang , Xiaoyu Shen , Wenjie Li , Wei Zhang

Recent advancement in code understanding and generation demonstrates that code LLMs fine-tuned on a high-quality instruction dataset can gain powerful capabilities to address wide-ranging code-related tasks. However, most previous existing…

Computation and Language · Computer Science 2025-02-12 Jian Yang , Wei Zhang , Jiaxi Yang , Yibo Miao , Shanghaoran Quan , Zhenhe Wu , Qiyao Peng , Liqun Yang , Tianyu Liu , Zeyu Cui , Binyuan Hui , Junyang Lin

Automated essay scoring (AES) systems increasingly rely on large language models, yet little is known about how architectural choices shape their performance across different essay quality levels. This paper evaluates single-agent and…

Computation and Language · Computer Science 2026-02-02 Jamiu Adekunle Idowu , Ahmed Almasoud

Behavioral analysis of tutoring dialogues is essential for understanding student learning, yet manual coding remains a bottleneck. We present a methodology where LLM coding agents autonomously improve the prompts used by LLM classifiers to…

Human-Computer Interaction · Computer Science 2026-03-31 Eason Chen , Isabel Wang , Nina Yuan , Sophia Judicke , Kayla Beigh , Xinyi Tang