English
Related papers

Related papers: RAVEL: Reasoning Agents for Validating and Evaluat…

200 papers

The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge…

Computation and Language · Computer Science 2026-05-05 Sangkwon Park , Donghun Kang , Jisoo Mok , Sungroh Yoon

Code reasoning tasks are increasingly crucial to evaluating large language models (LLMs). Yet most existing benchmarks rely on simplistic, LLM-generated snippets or human-written solutions to code challenges and often restrict inputs and…

Software Engineering · Computer Science 2026-04-15 Changshu Liu

Large Language Models (LLMs) deployed as autonomous agents commonly use Retrieval-Augmented Generation (RAG), feeding retrieved documents into the context window, which creates two problems: the risk of hallucination grows with context…

Information Retrieval · Computer Science 2026-03-25 Ivan Dobrovolskyi

Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of…

Databases · Computer Science 2025-04-03 Shreya Shankar , Tristan Chambers , Tarak Shah , Aditya G. Parameswaran , Eugene Wu

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

Artificial Intelligence · Computer Science 2026-05-21 Zhengkang Guo , Yiyang Li , Lin Qiu , Xiaohua Wang , Jingwen Xv , Dongyu Ru , Xiaoyu Li , Xiaoqing Zheng , Xuezhi Cao , Xunliang Cai

Complex dialog systems often use retrieved evidence to facilitate factual responses. Such RAG (Retrieval Augmented Generation) systems retrieve from massive heterogeneous data stores that are usually architected as multiple indexes or APIs…

Information Retrieval · Computer Science 2024-08-01 Ashutosh Joshi , Sheikh Muhammad Sarwar , Samarth Varshney , Sreyashi Nag , Shrivats Agrawal , Juhi Naik

Recent breakthroughs in large language models (LLMs), particularly in reasoning capabilities, have propelled Retrieval-Augmented Generation (RAG) to unprecedented levels. By synergizing retrieval mechanisms with advanced reasoning, LLMs can…

Information Retrieval · Computer Science 2025-04-25 Yunfan Gao , Yun Xiong , Yijie Zhong , Yuxi Bi , Ming Xue , Haofen Wang

The pace of evolution of Large Language Models (LLMs) necessitates new approaches for rigorous and comprehensive evaluation. Traditional human annotation is increasingly impracticable due to the complexities and costs involved in generating…

Computation and Language · Computer Science 2025-02-21 Arkil Patel , Siva Reddy , Dzmitry Bahdanau

Understanding and reasoning on the large-scale scientific literature is a crucial touchstone for large language model (LLM) based agents. However, existing works are mainly restricted to tool-free tasks within single papers, largely due to…

Artificial Intelligence · Computer Science 2026-02-02 Daoyu Wang , Mingyue Cheng , Shuo Yu , Zirui Liu , Ze Guo , Xin Li , Qi Liu

Individual neurons participate in the representation of multiple high-level concepts. To what extent can different interpretability methods successfully disentangle these roles? To help address this question, we introduce RAVEL (Resolving…

Computation and Language · Computer Science 2024-08-28 Jing Huang , Zhengxuan Wu , Christopher Potts , Mor Geva , Atticus Geiger

The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from…

Computation and Language · Computer Science 2026-01-09 Xianyang Liu , Yilin Liu , Shuai Wang , Hao Cheng , Andrew Estornell , Yuzhi Zhao , Jun Shu , Jiaheng Wei

Large language models (LLMs) have achieved remarkable progress in complex reasoning tasks, yet they remain fundamentally limited by their reliance on static internal knowledge and text-only reasoning. Real-world problem solving often…

Artificial Intelligence · Computer Science 2025-05-06 Joykirat Singh , Raghav Magazine , Yash Pandya , Akshay Nambi

The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models…

Computation and Language · Computer Science 2024-12-20 Yuan Xia , Jingbo Zhou , Zhenhui Shi , Jun Chen , Haifeng Huang

Despite impressive results on curated benchmarks, the practical impact of large language models (LLMs) on research-level neural theorem proving and proof autoformalization is still limited. We introduce RLMEval, an evaluation suite for…

Computation and Language · Computer Science 2025-10-30 Auguste Poiroux , Antoine Bosselut , Viktor Kunčak

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Artificial Intelligence · Computer Science 2025-11-05 Zhiwei Zhang , Xiaomin Li , Yudi Lin , Hui Liu , Ramraj Chandradevan , Linlin Wu , Minhua Lin , Fali Wang , Xianfeng Tang , Qi He , Suhang Wang

While explicit reasoning trajectories enhance model interpretability, existing paradigms often rely on monolithic chains that lack intermediate verification, allowing early errors to cascade unchecked. This lack of modularity impedes…

Computation and Language · Computer Science 2026-05-11 Yinsheng Yao , Jiehao Tang , Zhaozhen Yang , Dawei Cheng

The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating…

Computation and Language · Computer Science 2025-08-25 Minghao Li , Ying Zeng , Zhihao Cheng , Cong Ma , Kai Jia

Large Language Models (LLMs) are increasingly being used to automate programming tasks. Yet, LLMs' capabilities in reasoning about program semantics are still inadequately studied, leaving significant potential for further exploration. This…

Programming Languages · Computer Science 2025-05-30 Thanh Le-Cong , Bach Le , Toby Murray

Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of…

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing