English
Related papers

Related papers: Plantain: Plan-Answer Interleaved Reasoning

200 papers

When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facilitate an iterative reasoning and elicitation process, where the human's role is to guide the AI…

Artificial Intelligence · Computer Science 2026-04-10 Guilhem Fouilhé , Rebecca Eifler , Antonin Poché , Sylvie Thiébaux , Nicholas Asher

Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…

Artificial Intelligence · Computer Science 2023-05-31 Kanishk Gandhi , Dorsa Sadigh , Noah D. Goodman

Explaining how to get from A to B can be challenging. It requires mentally simulating what the listener will do based on what they are told. To capture this process, we propose a computational model that converts utterances into action…

Computation and Language · Computer Science 2026-05-12 Hanqi Zhou , Britt Besch , Charley M. Wu , Tobias Gerstenberg

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…

Artificial Intelligence · Computer Science 2026-05-28 Zhipeng Qian , Zihan Liang , Yufei Ma , Ben Chen , Huangyu Dai , Jiayi Ji , Chenyi Lei , Wenwu Ou , Xiaoshuai Sun , Qibin Hou

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

Artificial Intelligence · Computer Science 2025-10-08 Renee Ge , Qianli Liao , Tomaso Poggio

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Computation and Language · Computer Science 2025-12-09 Charlie Zhang , Graham Neubig , Xiang Yue

Information retrieval has long focused on ranking documents by semantic relatedness. Yet many real-world information needs demand more: enforcement of logical constraints, multi-step inference, and synthesis of multiple pieces of evidence.…

Information Retrieval · Computer Science 2026-02-04 Mohanna Hoveyda , Panagiotis Efstratiadis , Arjen de Vries , Maarten de Rijke

Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let…

Computation and Language · Computer Science 2024-04-23 Sachin Goyal , Ziwei Ji , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar , Vaishnavh Nagarajan

Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a conversational manner, human users can effectively influence…

Computation and Language · Computer Science 2024-10-02 Santosh Kumar Radha , Yasamin Nouri Jelyani , Ara Ghukasyan , Oktay Goktas

Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent studies focus on exploring various methods to equip LLMs with…

Computation and Language · Computer Science 2026-05-12 Luan Zhang , Dandan Song , Zhijing Wu , Zhengyu Chen , Chen Zhang , Yuhang Tian , Huipeng Ma , Chenhao Li , Changzhi Zhou , Xudong Li , Shuhao Zhang

This paper argues that model-free reinforcement learning (RL) agents, while lacking explicit planning mechanisms, exhibit behaviours that can be analogised to System 1 ("thinking fast") processes in human cognition. Unlike model-based RL…

Artificial Intelligence · Computer Science 2025-01-31 Hal Ashton , Matija Franklin

Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, context length limits, and degraded reasoning due to lost-in-the-middle effects. Iterative…

Computation and Language · Computer Science 2026-02-10 Yuchen Yan , Liang Jiang , Jin Jiang , Shuaicheng Li , Zujie Wen , Zhiqiang Zhang , Jun Zhou , Jian Shao , Yueting Zhuang , Yongliang Shen

Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing…

Computation and Language · Computer Science 2026-05-08 Yijia Zheng , Marcel Worring

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Computation and Language · Computer Science 2025-04-15 Haotian Wang , Han Zhao , Shuaiting Chen , Xiaoyu Tian , Sitong Zhao , Yunjie Ji , Yiping Peng , Xiangang Li

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and…

Computation and Language · Computer Science 2023-08-22 Pengbo Hu , Ji Qi , Xingyu Li , Hong Li , Xinqi Wang , Bing Quan , Ruiyu Wang , Yi Zhou

Chain-of-Thought reasoning has emerged as a pivotal methodology for enhancing model inference capabilities. Despite growing interest in Chain-of-Thought reasoning, its underlying mechanisms remain unclear. This paper explores the working…

Computation and Language · Computer Science 2025-09-03 Hao Yang , Zhiyu Yang , Yunjie Zhang , Shanyi Zhu , Lin Yang

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Computation and Language · Computer Science 2026-03-30 Hongxiang Zhang , Yuan Tian , Tianyi Zhang

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

Computation and Language · Computer Science 2026-03-09 Yunlong Chu , Minglai Shao , Yuhang Liu , Bing Hao , Yumeng Lin , Jialu Wang , Ruijie Wang

Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver. In this work, we make a stronger claim -- many reasoning problems…

Computation and Language · Computer Science 2025-02-25 Nikunj Saunshi , Nishanth Dikkala , Zhiyuan Li , Sanjiv Kumar , Sashank J. Reddi

Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…

Computation and Language · Computer Science 2025-07-04 Tao Xiong , Xavier Hu , Wenyan Fan , Shengyu Zhang