English
Related papers

Related papers: Calibrate-Then-Act: Cost-Aware Exploration in LLM …

200 papers

Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a…

Artificial Intelligence · Computer Science 2026-05-19 Romain Cosentino , Sarath Shekkizhar , Adam Earle , Silvio Savarese

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

Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs). In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents…

Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet…

Computation and Language · Computer Science 2026-04-14 Dat Tran , Douwe Kiela

Deep research agents rely on iterative retrieval and reasoning to answer complex queries, but scaling test-time computation raises significant efficiency concerns. We study how to allocate reasoning budget in deep search pipelines, focusing…

Information Retrieval · Computer Science 2026-01-21 Sahel Sharifymoghaddam , Jimmy Lin

The rise of LLM-based agents shows great potential to revolutionize task planning, capturing significant attention. Given that these agents will be integrated into high-stake domains, ensuring their reliability and safety is crucial. This…

Computation and Language · Computer Science 2024-10-07 Wenyue Hua , Xianjun Yang , Mingyu Jin , Zelong Li , Wei Cheng , Ruixiang Tang , Yongfeng Zhang

Quantitative requirements play an important role in the context of multi-agent systems, where there is often a trade-off between the tasks of individual agents and the constraints that the agents must jointly adhere to. We study multi-agent…

Logic in Computer Science · Computer Science 2024-12-18 Rafael Dewes , Rayna Dimitrova

Large Language Models (LLMs) have demonstrated potential as effective search relevance evaluators. However, there is a lack of comprehensive guidance on which models consistently perform optimally across various contexts or within specific…

Machine Learning · Computer Science 2024-10-29 Silvia Terragni , Hoang Cuong , Joachim Daiber , Pallavi Gudipati , Pablo N. Mendes

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet…

Artificial Intelligence · Computer Science 2026-05-18 Igor Bogdanov , Chung-Horng Lung , Thomas Kunz , Jie Gao , Adrian Taylor , Marzia Zaman

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature…

Computation and Language · Computer Science 2026-04-15 Raeyoung Chang , Dongwook Kwon , Jisoo Lee , Nikhil Verma

Common approaches for task-agnostic exploration learn tabula-rasa --the agent assumes isolated environments and no prior knowledge or experience. However, in the real world, agents learn in many environments and always come with prior…

Machine Learning · Computer Science 2021-11-29 Simone Parisi , Victoria Dean , Deepak Pathak , Abhinav Gupta

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…

Computation and Language · Computer Science 2025-11-12 Zhiheng Xi , Chenyang Liao , Guanyu Li , Yajie Yang , Wenxiang Chen , Zhihao Zhang , Binghai Wang , Senjie Jin , Yuhao Zhou , Jian Guan , Wei Wu , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling…

Multiagent Systems · Computer Science 2025-11-12 Haolun Wu , Zhenkun Li , Lingyao Li

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Machine Learning · Computer Science 2026-04-03 Zhanzhi Lou , Hui Chen , Yibo Li , Qian Wang , Bryan Hooi

Architecture evaluation methods have been extensively used to evaluate software designs. Several evaluation methods have been proposed to analyze tradeoffs between different quality attributes. Also, having competing qualities leads to…

Software Engineering · Computer Science 2026-04-01 Rafael Capilla , Jorge Andrés Díaz-Pace , Yamid Ramírez , Jennifer Pérez , Vanessa Rodríguez-Horcajo

While it is known that communication facilitates cooperation in multi-agent settings, it is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other. Much research on communication…

This study introduces \textbf{InteractEval}, a framework that integrates human expertise and Large Language Models (LLMs) using the Think-Aloud (TA) method to generate attributes for checklist-based text evaluation. By combining human…

Computation and Language · Computer Science 2025-02-21 SeongYeub Chu , JongWoo Kim , MunYong Yi

Multi-agent LLM systems fail to realize parallel speedups due to costly coordination. We present CodeCRDT, an observation-driven coordination pattern where agents coordinate by monitoring a shared state with observable updates and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-23 Sergey Pugachev

The ReAct (Reasoning + Action) capability in large language models (LLMs) has become the foundation of modern agentic systems. Recent LLMs, such as DeepSeek-R1 and OpenAI o1/o3, exemplify this by emphasizing reasoning through the generation…

Artificial Intelligence · Computer Science 2025-05-20 Mrinal Rawat , Ambuje Gupta , Rushil Goomer , Alessandro Di Bari , Neha Gupta , Roberto Pieraccini

Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approach this problem from a case-based perspective to present…

Artificial Intelligence · Computer Science 2026-05-15 Renning Pang , Tian Lan , Leyuan Liu , Piao Tong , Sheng Cao , Xiaosong Zhang