English
Related papers

Related papers: The Reasoning Trap: An Information-Theoretic Bound…

200 papers

Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet the failure dynamics of homogeneous debate remain poorly…

Multiagent Systems · Computer Science 2026-05-05 Blaž Bertalanič , Carolina Fortuna

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value…

Multiagent Systems · Computer Science 2026-04-30 Ariel Sela

Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior work suggests that forcing the CoT to remain in the input language (\emph{native…

Computation and Language · Computer Science 2026-05-27 Maxence Lasbordes , Amélie Chatelain , Djamé Seddah

LLMs demonstrate performance comparable to human abilities in complex tasks such as mathematical reasoning, but their robustness in mathematical reasoning under minor input perturbations still lacks systematic investigation. Existing…

Artificial Intelligence · Computer Science 2025-11-12 Zhishen Sun , Guang Dai , Haishan Ye

Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning into a falsifiable and auditable…

Artificial Intelligence · Computer Science 2025-10-27 Hongwei Zhang , Ji Lu , Shiqing Jiang , Chenxiang Zhu , Li Xie , Chen Zhong , Haoran Chen , Yurui Zhu , Yongsheng Du , Yanqin Gao , Lingjun Huang , Baoli Wang , Fang Tan , Peng Zou

With the rapid advancements in large language models (LLMs), debating tasks, such as argument quality assessment and debate process simulation, have made significant progress. However, existing LLM-based debating systems focus on responding…

Computation and Language · Computer Science 2025-06-24 Fuyu Wang , Jiangtong Li , Kun Zhu , Changjun Jiang

Small Language Models (SLMs) offer privacy and efficiency for educational deployment, yet their utility depends on reliable multistep reasoning. Existing benchmarks often prioritize final answer accuracy, obscuring 'right answer, wrong…

Computation and Language · Computer Science 2026-01-08 Nicy Scaria , Silvester John Joseph Kennedy , Krishna Agarwal , Diksha Seth , Deepak Subramani

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we…

Computation and Language · Computer Science 2025-12-09 Jiaru Zou , Xiyuan Yang , Ruizhong Qiu , Gaotang Li , Katherine Tieu , Pan Lu , Ke Shen , Hanghang Tong , Yejin Choi , Jingrui He , James Zou , Mengdi Wang , Ling Yang

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the…

Artificial Intelligence · Computer Science 2025-05-30 Zidi Xiong , Shan Chen , Zhenting Qi , Himabindu Lakkaraju

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classification. This is due to (1) the lack of reasoning ability…

Computation and Language · Computer Science 2023-10-10 Xiaofei Sun , Xiaoya Li , Jiwei Li , Fei Wu , Shangwei Guo , Tianwei Zhang , Guoyin Wang

Large language models (LLMs) have shown promise in medical domains, but their ability to handle specialized neurological reasoning requires systematic evaluation. We developed a comprehensive benchmark using 305 questions from Israeli Board…

Information Retrieval · Computer Science 2025-08-21 Moran Sorka , Alon Gorenshtein , Dvir Aran , Shahar Shelly

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it…

Artificial Intelligence · Computer Science 2025-05-30 Xinjie Zhao , Fan Gao , Xingyu Song , Yingjian Chen , Rui Yang , Yanran Fu , Yuyang Wang , Yusuke Iwasawa , Yutaka Matsuo , Irene Li

We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with complementary but incomplete views must coordinate through…

Computation and Language · Computer Science 2026-04-29 Abhijnan Nath , Hannah VanderHoeven , Nikhil Krishnaswamy

Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under adversarial prompting. Existing safety approaches -- such as reinforcement learning from human…

Artificial Intelligence · Computer Science 2026-03-20 Zou Qiang

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Machine Learning · Computer Science 2025-10-03 Aniket Vashishtha , Qirun Dai , Hongyuan Mei , Amit Sharma , Chenhao Tan , Hao Peng

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Machine Learning · Computer Science 2026-05-22 Srujan P Mule , Aniketh Garikaparthi , Manasi Patwardhan

Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate…

Computation and Language · Computer Science 2025-06-10 Pradyumna Shyama Prasad , Minh Nhat Nguyen

Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational…

The $\textit{LLM-as-a-judge}$ paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluate text strictly on its semantic content, impervious to surrounding…

Artificial Intelligence · Computer Science 2026-04-17 Manan Gupta , Inderjeet Nair , Lu Wang , Dhruv Kumar
‹ Prev 1 8 9 10 Next ›