Long-Horizon Agent Tasks

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 125% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 127

All topics

Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
Apr 17, 2026Luay Gharzeddine, Samer SaabMulti-Agent Coordination Multi-Agent Orchestration
1Dept of Computer Science, Lebanese American University. · 2*Dept of Electrical and Computer Engineering, Lebanese American University.
Autogenesis: A Self-Evolving Agent Protocol
Apr 16, 2026Wentao Zhang, Zhe Zhao, Haibin Wen +4Multi-Agent LLM Systems LLM Agent Self-Improvement
Nanyang Technological University · Stanford University · City University of Hong Kong +1
Effective Strategies for Asynchronous Software Engineering Agents
Mar 23, 2026Jiayi Geng, Graham NeubigMulti-Agent Coordination Software Engineering Agents
Carnegie Mellon University, Language Technologies Institute
Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
Feb 3, 2026Jinwoo Choi, Sang-Hyun Lee, Seung-Woo SeoReinforcement Learning Hierarchical RL
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea · Department of Automotive Engineering, Ajou University, Gyeonggi-do, South Korea
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning
Jan 17, 2026Bingxuan Li, Jeonghwan Kim, Cheng Qian +4Long-Horizon Agent Tasks RL for LLM Agents
University of Illinois at Urbana-Champaign · Viven
MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
Jan 14, 2026Handi Chen, Running Zhao, Xiuzhe Wu +2Multi-Agent LLM Systems Multi-Agent Coordination
The University of Hong Kong
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
Jan 13, 2026Youwei Liu, Jian Wang, Hanlin Wang +2World Model-Based Planning Model-Based Planning
Central South University · Department of Computing, The Hong Kong Polytechnic University · College of Computer Science, Sichuan University

Apr 17, 2026, cs.MAJ/K move · Enter open · S save

Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows

Luay Gharzeddine, Samer Saab

1Dept of Computer Science, Lebanese American University. · 2*Dept of Electrical and Computer Engineering, Lebanese American University.

Multi-Agent Coordination Multi-Agent Orchestration LLM Agent Workflow Optimization AI Agent Benchmarks Tool-Using Agents Graph-Based Planning+1

Open paper AskPDF arXiv

Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibility can also introduce coordination overhead and substantial inference cost. We study complete cyclic subtask graphs, a deliberately maximally flexible multi-agent architecture in which executable subtask nodes are fully connected and a unified state-analysis-and-routing agent selects transitions using natural-language criteria. This makes unrestricted revisitation explicit and directly analyzable at the subtask level. We evaluate task-specific (Spec-Cyc) and benchmark-generic (Gen-Cyc) graphs on TextCraft, ALFWorld, and Finance-Agent, with ablations over planner/executor/router strength, tool exposure (generalist vs specialized),

n

-shot successful trajectory summaries, and fault-injected random subtask perturbations. The benchmarks expose three distinct regimes. ALFWorld highlights a setting where explicit revisitation supports recovery and exploration; TextCraft, a largely prerequisite-chain domain, often favors the efficiency of simpler forward execution; and Finance-Agent remains bottlenecked by retrieval, grounding, and evidence synthesis more than by workflow flexibility alone. Shared-win token comparisons further show that the added flexibility can be substantially more expensive than a single ReAct agent. Overall, we use complete cyclic subtask graphs as a maximally flexible experimental lens for measuring when multi-agent revisitation helps, when it mainly adds coordination cost, and when external task bottlenecks dominate.

Momentum

Related topics

Latest papers 127