English
Related papers

Related papers: PACEvolve++: Improving Test-time Learning for Evol…

200 papers

Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement…

Artificial Intelligence · Computer Science 2026-02-26 Lunjun Zhang , Ryan Chen , Bradly C. Stadie

Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutionary search with large…

Artificial Intelligence · Computer Science 2026-05-26 Anja Surina , Amin Mansouri , Lars Quaedvlieg , Amal Seddas , Maryna Viazovska , Emmanuel Abbe , Caglar Gulcehre

Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges,…

Computation and Language · Computer Science 2026-04-20 Shidong Yang , Ziyu Ma , Tongwen Huang , Yiming Hu , Yong Wang , Xiangxiang Chu

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…

Robotics · Computer Science 2020-08-03 Zuxin Liu , Baiming Chen , Hongyi Zhou , Guru Koushik , Martial Hebert , Ding Zhao

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…

Computation and Language · Computer Science 2025-06-19 Peiyan Zhang , Haibo Jin , Leyang Hu , Xinnuo Li , Liying Kang , Man Luo , Yangqiu Song , Haohan Wang

We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and…

Artificial Intelligence · Computer Science 2026-05-29 Henrique Assumpção , Diego Ferreira , Leandro Campos , Fabricio Murai

This paper focuses on a class of reinforcement learning problems where significant events are rare and limited to a single positive reward per episode. A typical example is that of an agent who has to choose a partner to cooperate with,…

Machine Learning · Computer Science 2022-10-12 Paul Ecoffet , Nicolas Fontbonne , Jean-Baptiste André , Nicolas Bredeche

We propose a novel reinforcement learning-based approach for adaptive and iterative feature selection. Given a masked vector of input features, a reinforcement learning agent iteratively selects certain features to be unmasked, and uses…

Machine Learning · Computer Science 2020-05-26 Uri Shaham , Tom Zahavy , Cesar Caraballo , Shiwani Mahajan , Daisy Massey , Harlan Krumholz

Large language models (LLMs) have been increasingly applied to tasks in language understanding and interactive decision-making, with their impressive performance largely attributed to the extensive domain knowledge embedded within them.…

Artificial Intelligence · Computer Science 2024-10-16 Zhiyuan Sun , Haochen Shi , Marc-Alexandre Côté , Glen Berseth , Xingdi Yuan , Bang Liu

The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference…

Computation and Language · Computer Science 2025-07-22 Haoran Sun , Zekun Zhang , Shaoning Zeng

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Off-policy learning algorithms have been known to be sensitive to the choice of hyper-parameters. However, unlike near on-policy algorithms for which hyper-parameters could be optimized via e.g. meta-gradients, similar techniques could not…

Machine Learning · Computer Science 2020-06-16 Yunhao Tang , Krzysztof Choromanski

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Neural and Evolutionary Computing · Computer Science 2025-05-26 Rishi Hazra , Alkis Sygkounas , Andreas Persson , Amy Loutfi , Pedro Zuidberg Dos Martires

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across…

Machine Learning · Computer Science 2022-06-22 Xingyu Liu , Deepak Pathak , Kris M. Kitani

The reasoning frontier of Large Language Models (LLMs) has advanced significantly through modern post-training paradigms (e.g., Reinforcement Learning from Verifiable Rewards (RLVR)). However, the efficacy of these methods remains…

Machine Learning · Computer Science 2026-05-13 Liqin Ye , Yanbin Yin , Michael Galarnyk , Yuzhao Heng , Sudheer Chava , Chao Zhang

Evolutionary algorithms excel in solving complex optimization problems, especially those with multiple objectives. However, their stochastic nature can sometimes hinder rapid convergence to the global optima, particularly in scenarios…

Neural and Evolutionary Computing · Computer Science 2024-05-10 Zeyi Wang , Songbai Liu , Jianyong Chen , Kay Chen Tan

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…

Artificial Intelligence · Computer Science 2026-05-12 Zhiyuan Fan , Wenwei Jin , Feng Zhang , Bin Li , Yihong Dong , Yao Hu , Jiawei Li

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

Machine Learning · Computer Science 2025-10-09 Arshika Lalan , Rajat Ghosh , Aditya Kolsur , Debojyoti Dutta

In computer interfaces in general, especially in information retrieval tasks, it is important to be able to quickly find and retrieve information. State of the art approach, used, for example, in search engines, is not effective as it…

Information Retrieval · Computer Science 2015-02-20 Dmytro Filatov , Taras Filatov

Recent advancements in prompt engineering strategies, such as Chain-of-Thought (CoT) and Self-Discover, have demonstrated significant potential in improving the reasoning abilities of Large Language Models (LLMs). However, these…

Computation and Language · Computer Science 2024-10-15 Krishna Aswani , Huilin Lu , Pranav Patankar , Priya Dhalwani , Iris Tan , Jayant Ganeshmohan , Simon Lacasse