English
Related papers

Related papers: Decocted Experience Improves Test-Time Inference i…

200 papers

We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agent optimizes its response in context using self-assessed or…

Machine Learning · Computer Science 2026-03-03 Tianrun Yu , Yuxiao Yang , Zhaoyang Wang , Kaixiang Zhao , Porter Jenkins , Xuchao Zhang , Chetan Bansal , Huaxiu Yao , Weitong Zhang

The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capability of the model to accurately reason over that context…

Computation and Language · Computer Science 2024-10-07 Huayang Li , Pat Verga , Priyanka Sen , Bowen Yang , Vijay Viswanathan , Patrick Lewis , Taro Watanabe , Yixuan Su

Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and updated, while paying less attention to how experience should…

Computation and Language · Computer Science 2026-05-11 Weixiang Zhao , Yingshuo Wang , Yichen Zhang , Yanyan Zhao , Yu Zhang , Yang Wu , Dandan Tu , Bing Qin , Ting Liu

Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the…

Artificial Intelligence · Computer Science 2026-04-22 Jingxuan Chen , Mohammad Taher Pilehvar , Jose Camacho-Collados

Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code generation, numerical reasoning, and dialog. Existing work…

Machine Learning · Computer Science 2024-10-08 Mehul Damani , Idan Shenfeld , Andi Peng , Andreea Bobu , Jacob Andreas

Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their…

Computation and Language · Computer Science 2026-03-13 Yuling Jiao , Yanming Lai , Huazhen Lin , Wensen Ma , Houduo Qi , Defeng Sun

Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training…

As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this challenge -- extracting reusable…

Artificial Intelligence · Computer Science 2026-04-20 Xing Zhang , Guanghui Wang , Yanwei Cui , Wei Qiu , Ziyuan Li , Bing Zhu , Peiyang He

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…

Computation and Language · Computer Science 2024-10-10 Chufan Shi , Haoran Yang , Deng Cai , Zhisong Zhang , Yifan Wang , Yujiu Yang , Wai Lam

Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify…

Computation and Language · Computer Science 2025-10-08 Yufeng Du , Minyang Tian , Srikanth Ronanki , Subendhu Rongali , Sravan Bodapati , Aram Galstyan , Azton Wells , Roy Schwartz , Eliu A Huerta , Hao Peng

When reading long-form text, human cognition is complex and structurized. While large language models (LLMs) process input contexts through a causal and sequential perspective, this approach can potentially limit their ability to handle…

Computation and Language · Computer Science 2024-11-01 Kai Liu , Zhihang Fu , Chao Chen , Wei Zhang , Rongxin Jiang , Fan Zhou , Yaowu Chen , Yue Wu , Jieping Ye

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…

Machine Learning · Computer Science 2025-09-26 Sheng Liu , Tianlang Chen , Pan Lu , Haotian Ye , Yizheng Chen , Lei Xing , James Zou

Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to…

Artificial Intelligence · Computer Science 2025-09-25 Yuanxin Wang , Pawel Filipczuk , Anisha Garg , Amaan Dhada , Mohammad Hassanpour , David Bick , Ganesh Venkatesh

Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this…

Computation and Language · Computer Science 2026-02-25 Pietro Bernardelle , Stefano Civelli , Kevin Roitero , Gianluca Demartini

Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a…

Computation and Language · Computer Science 2025-05-29 Yufan Zhuang , Xiaodong Yu , Jialian Wu , Ximeng Sun , Ze Wang , Jiang Liu , Yusheng Su , Jingbo Shang , Zicheng Liu , Emad Barsoum

Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at…

Computation and Language · Computer Science 2026-03-30 Wenbo Gao , Renxi Liu , Xian Wang , Fang Guo , Shuai Yang , Xi Chen , Hui-Ling Zhen , Hanting Chen , Weizhe Lin , Xiaosong Li , Yaoyuan Wang

Scaling laws have transformed our understanding of large language models by linking upstream metrics like cross-entropy loss to design factors such as model size, training data, and compute. However, these conventional laws fail to capture…

Computation and Language · Computer Science 2025-10-17 Kyle Montgomery , David Park , Jianhong Tu , Michael Bendersky , Beliz Gunel , Dawn Song , Chenguang Wang

While reaching for NLP systems that maximize accuracy, other important metrics of system performance are often overlooked. Prior models are easily forgotten despite their possible suitability in settings where large computing resources are…

Computation and Language · Computer Science 2024-04-19 Mahammed Kamruzzaman , Gene Louis Kim

Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…

Artificial Intelligence · Computer Science 2025-08-26 Dulhan Jayalath , James Bradley Wendt , Nicholas Monath , Sandeep Tata , Beliz Gunel

Recent advancements in large language models (LLMs) often rely on generating intermediate reasoning steps to enhance accuracy. However, little work has examined how reasoning utility contributes to the final answer's correctness. Due to the…

Computation and Language · Computer Science 2025-08-29 Xu Guo