ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “long-horizon tasks”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.LGcs.AIcs.CLRecentMay 28, 2026

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding +3 more

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical st…

View →
cs.AIRecentMay 31, 2026

Can LLM Agents Sustain Long-Horizon Organizational Dynamics?

Xuancheng Zhu, Yang Yue, Shuaibing Wan, Zihan Dou +3 more

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating t…

View →
cs.AIcs.CLcs.CREmpiricalRecentJul 22, 2026

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety

Yuan Xiong, Linji Hao, Shizhu He, Yequan Wang +1 more

The paper proposes Janus, a framework for long-horizon agent safety using multi-agent simulation and CoAA-RL, which trains guards to anticipate risks and make safety judgments based on both observed p…

View →
cs.AIEmpiricalRecentOct 8, 2026

On the estimation and validity of AI time horizons---a statistical look at the METR plot

Drew T. Nguyen, William Fithian

This paper recompiles time horizons for AI capabilities using splines and item-response theory to improve their interpretability.

View →
cs.ROcs.AIEmpiricalRecentJul 22, 2026

Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments

Md Ridwan Hossain Talukder, Roshan Dhakal, Elizabeth Phillips, Gregory J. Stein

A model-based planner is presented that minimizes immediate cost and aggregated expected future cost across all robots in a task planning scenario with robots sharing a persistent environment.

View →
cs.CCcs.DSTheoreticalRecentOct 26, 2026

The Complexity of Value Optimization in Sporadic Task Systems

Christopher Harbourne, Nathan Fisher, Kecheng Yang, Pontus Ekberg +2 more

This paper studies the complexity of Value-based Task Selection (VTS) in real-time systems.

View →
cs.AIEmpiricalRecentAug 5, 2026

Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning

Boxiu Li, Zimo Wen, Yijia Fan, Junxiang Lei +22 more

Argus is a persistent, self-evolving runtime system that achieves better long-horizon reasoning results than Direct Copilot in seven GPT-5.5 benchmark arenas, with improvements in solve-input tokens,…

View →
cs.AIcs.CLcs.SEEmpiricalRecentJun 16, 2026

CEO-Bench: Can Agents Play the Long Game?

Haozhe Chen, Karthik Narasimhan, Zhuang Liu

Evaluates the capabilities of language model agents in a simulated real-world task.

View →
cs.NEEmpiricalRecentOct 18, 2026

Let Them Sleep: Recursive Self-Pruning Memory for Long-Horizon LLM Agents

Kargi Chauhan, Sadiba Nusrat Nur, Pratibha Revankar, Kyle Montgomery +1 more

The paper introduces RSPM, a memory management technique for agents that improves performance by pruning and forgetting unnecessary information.

View →
cs.AIcs.CLRecentMay 28, 2026

GTA: Generating Long-Horizon Tasks for Web Agents at Scale

Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou +3 more

The paper introduces GTA, a scalable framework for generating realistic, multi-hop web-agent tasks with dense, executable trajectories, addressing the current lack of process-level supervision in web…

View →
cs.AIRecentMay 28, 2026

Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling

Shijie Cao, Yuan Yuan, Jing Liu

RACE-Sched is an asynchronous agentic framework that successfully integrates low-latency, real-time scheduling decisions with advanced, long-horizon reasoning provided by Large Language Models.

View →
cs.CLRecentMay 31, 2026

Robust Asynchronous Planning via Auto-Formalization

Jiayi Zhang, Jianing Yin, Ben Zhou, Li Zhang

The paper introduces new benchmarks for complex asynchronous planning and demonstrates that general constraint satisfaction formalizers (like CP-SAT) significantly outperform direct LLM planning or tr…

View →
cs.CLcs.AIcs.LGEmpiricalRecentJul 27, 2026

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao

This paper introduces a controlled environment to study multi-turn long-horizon planning ability acquisition, shaping, and integration in foundation model agents.

View →
cs.AIRecentMay 27, 2026

GONDOR to the Rescue: Satisficing Planning with Low Memory

Yonatan Vernik, Alexander Tuisov, Alexander Shleyfman

The paper introduces GONDOR, a memory-efficient extension of Greedy Best-First Search (GBFS) that enables search continuation under strict memory constraints by periodically compressing the search tre…

View →
cs.DCEmpiricalRecentJun 11, 2026

Finding Conservation Laws of Large Dynamical Systems with Tasks and Futures: A Case Study in Utilizing Dynamic Data Dependencies

Rüdiger Nather

The paper introduces a new construct, await_delete, to allow safe value reuse in futures and presents a novel future-based algorithm for block-wise inversion of dense, symmetric matrices.

View →
cs.AIRecentMay 28, 2026

Transforming and Encoding FTS for SAT Solving: What Helps, What Hurts (Extended Version)

João Filipe, Álvaro Torralba, Gregor Behnke

This paper investigates various methods for encoding factored tasks, a compact planning representation, into propositional logic for use with SAT solvers, analyzing the impact of encoding choices and…

View →