English
Related papers

Related papers: Polaris: A G\"odel Agent Framework for Small Langu…

200 papers

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined…

Artificial Intelligence · Computer Science 2025-06-03 Xunjian Yin , Xinyi Wang , Liangming Pan , Li Lin , Xiaojun Wan , William Yang Wang

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Binfeng Xu , Hao Zhang , Shaokun Zhang , Songyang Han , Mingjie Liu , Jian Hu , Shizhe Diao , Zhenghui Jin , Yunheng Zou , Michael Demoret , Jan Kautz , Yi Dong

Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic…

Artificial Intelligence · Computer Science 2026-01-21 Zahra Moslemi , Keerthi Koneru , Yen-Ting Lee , Sheethal Kumar , Ramesh Radhakrishnan

The growing scale, complexity, interconnectivity, and autonomy of modern software ecosystems introduce unprecedented uncertainty, challenging the foundations of traditional self-adaptation. Existing approaches, typically rule-driven…

Software Engineering · Computer Science 2025-12-09 Divyansh Pandey , Vyakhya Gupta , Prakhar Singhal , Karthik Vaidhyanathan

Large language models enable flexible multi-agent planning but remain fragile in practice: verification is often circular, state changes are not tracked for repair, and small faults trigger costly global recomputation. We present ALAS, a…

Multiagent Systems · Computer Science 2025-11-06 Longling Geng , Edward Y. Chang

Reinforcement Learning has emerged as a dominant post-training approach to elicit agentic RAG behaviors such as search and planning from language models. Despite its success with larger models, applying RL to compact models (e.g., 0.5--1B…

Computation and Language · Computer Science 2026-04-28 Rikuto Kotoge , Mai Nishimura , Jiaxin Ma

Large language model agents often fail to accumulate knowledge from experience, treating each task as an independent challenge. Recent methods extract experience as flattened textual knowledge, which cannot capture procedural logic of…

Artificial Intelligence · Computer Science 2026-02-02 Libin Qiu , Zhirong Gao , Junfu Chen , Yuhang Ye , Weizhi Huang , Xiaobo Xue , Wenkai Qiu , Shuo Tang

Large-scale industrial recommenders typically use a fixed multi-stage pipeline (recall, ranking, re-ranking) and have progressed from collaborative filtering to deep and large pre-trained models. However, both multi-stage and so-called One…

Information Retrieval · Computer Science 2026-04-10 Jinxin Hu , Hao Deng , Lingyu Mu , Hao Zhang , Shizhun Wang , Yu Zhang , Xiaoyi Zeng

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models. Yet existing methods share a common blind spot: they optimize policies…

Machine Learning · Computer Science 2026-04-29 Huaiyang Wang , Xiaojie Li , Deqing Wang , Haoyi Zhou , Zixuan Huang , Yaodong Yang , Jianxin Li , Yikun Ban

Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct)…

Artificial Intelligence · Computer Science 2025-09-09 Chunlong Wu , Ye Luo , Zhibo Qu , Min Wang

We present a framework for evaluating and benchmarking logical reasoning agents when assessment itself must be reproducible, auditable, and robust to execution failures. Building on agentified assessment, we use an assessor agent to issue…

Artificial Intelligence · Computer Science 2026-04-03 Zhiyu Ni , Yifeng Xiao , Zheng Liang

Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks limit current systems. First, existing tool-use harnesses…

Computation and Language · Computer Science 2026-05-12 Shijue Huang , Hangyu Guo , Chenxin Li , Junting Lu , Xinyu Geng , Zhaochen Su , Zhenyu Li , Shuang Chen , Hongru Wang , Yi R. Fung

Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not…

Artificial Intelligence · Computer Science 2025-12-10 Christopher Cruz

Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Yunpeng Zhou

A significant challenge for robot learning research is our ability to accurately measure and compare the performance of robot policies. Benchmarking in robotics is historically challenging due to the stochasticity, reproducibility, and…

Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or reward engineering? We argue the answer is yes, under conditions we characterise…

Robotics · Computer Science 2026-03-06 Vaishak Kumar

While humans readily generalize abstract concepts to more complex or larger tasks, building Reinforcement Learning (RL) systems with this ability remains elusive. Here, we present the first theoretical model of how such Out-of-Distribution…

Machine Learning · Computer Science 2026-05-21 Nasehatul Mustakim , Lucas Lehnert

Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making. We first report our Gemini Plays…

Machine Learning · Computer Science 2026-05-12 Seth Karten , Joel Zhang , Tersoo Upaa , Ruirong Feng , Wenzhe Li , Chengshuai Shi , Chi Jin , Kiran Vodrahalli

ASP programs are a convenient tool for problem solving, whereas with large problem instances the size of the state space can be prohibitive. We consider abstraction as a means of over-approximation and introduce a method to automatically…

Logic in Computer Science · Computer Science 2018-09-19 Zeynep G. Saribatur , Thomas Eiter

Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA - a framework for designing model-based agents operating in mixed…

Artificial Intelligence · Computer Science 2024-12-04 Shiwali Mohan , Wiktor Piotrowski , Roni Stern , Sachin Grover , Sookyung Kim , Jacob Le , Johan De Kleer
‹ Prev 1 2 3 10 Next ›