English
Related papers

Related papers: Agentic Confidence Calibration

200 papers

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…

Artificial Intelligence · Computer Science 2026-04-14 Anushree Sinha , Srivaths Ranganathan , Debanshu Das , Abhishek Dharmaratnakar

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…

Software Engineering · Computer Science 2026-01-07 Saba Naqvi , Mohammad Baqar , Nawaz Ali Mohammad

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…

Computation and Language · Computer Science 2024-10-29 Yukun Huang , Yixin Liu , Raghuveer Thirukovalluru , Arman Cohan , Bhuwan Dhingra

Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external data sources. Existing strategies fall into two paradigms based on planning horizon: (1)…

Computation and Language · Computer Science 2026-05-12 Naoki Otani , Nikita Bhutani , Hannah Kim , Dan Zhang , Estevam Hruschka

Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to…

Productive human-AI collaboration requires appropriate reliance, yet contemporary AI systems are often miscalibrated, exhibiting systematic overconfidence or underconfidence. We investigate whether humans can learn to mentally recalibrate…

Human-Computer Interaction · Computer Science 2026-03-25 ZhaoBin Li , Mark Steyvers

Deep clustering has exhibited remarkable performance; however, the over confidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been over looked…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Yuheng Jia , Jianhong Cheng , Hui Liu , Junhui Hou

The challenge is growing towards extreme and short-duration rainfall events like a cloudburst that are peculiar to the traditional forecasting systems, in which the predictions and the response are taken as two distinct processes. The paper…

Artificial Intelligence · Computer Science 2025-12-01 Toqeer Ali Syed , Sohail Khan , Salman Jan , Gohar Ali , Muhammad Nauman , Ali Akarma , Ahmad Ali

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their…

Computation and Language · Computer Science 2024-03-26 Jiahui Geng , Fengyu Cai , Yuxia Wang , Heinz Koeppl , Preslav Nakov , Iryna Gurevych

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…

Artificial Intelligence · Computer Science 2026-05-12 Kai Pan

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…

Artificial Intelligence · Computer Science 2026-03-16 Orit Shahnovsky , Rotem Dror

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Machine Learning · Computer Science 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv

Human trust in automation plays an essential role in interactions between humans and automation. While a lack of trust can lead to a human's disuse of automation, over-trust can result in a human trusting a faulty autonomous system which…

Human-Computer Interaction · Computer Science 2023-04-17 Kumar Akash , Griffon McMahon , Tahira Reid , Neera Jain

The quality assessment of Artificial Intelligence (AI) systems is a fundamental challenge due to their inherently probabilistic nature. Standards such as ISO/IEC 25059 provide a quality model, but they lack practical and statistically…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current…

Machine Learning · Computer Science 2024-12-05 Zheng Zhang , Cuong Nguyen , Kevin Wells , Thanh-Toan Do , David Rosewarne , Gustavo Carneiro

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…

Software Engineering · Computer Science 2026-05-12 Reshabh K Sharma , Shraddha Barke , Benjamin Zorn

As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…

Software Engineering · Computer Science 2026-01-01 Tao Dong , Harini Sampath , Ja Young Lee , Sherry Y. Shi , Andrew Macvean
‹ Prev 1 8 9 10 Next ›