Lune

ACL Findings2026

InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents

Chenglin Yu, Yuchen Wang, Songmiao Wang, Hongxia Yang, Li Ming

Abstract

LLM agents can reason and use tools, but they often break down on long-horizon tasks due to unbounded context growth and accumulated errors. Common remedies such as context compression or retrieval-augmented prompting introduce trade-offs between information fidelity and reasoning stability. We present InfiAgent, a general-purpose framework that keeps the agent's reasoning context strictly bounded regardless of task duration by externalizing persistent state into a filecentric state abstraction. At each step, the agent reconstructs context from a workspace state snapshot plus a fixed window of recent actions. Experiments on DeepResearch and an 80-paper literature review task show that, without task-specific fine-tuning, InfiAgent with a 20B open-source model is competitive with larger proprietary systems and maintains substantially higher long-horizon coverage than context-centric baselines. These results support explicit state externalization as a practical foundation for stable long-horizon agents.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. DeepResearch Bench: A Comprehensive Benchmark for Deep Research AgentsMingxuan Du, Benfeng Xu, Chiwei Zhu, Licheng Zhang et al.ICLR 2026 · 250 citations
  2. Richelieu: Self-Evolving LLM-Based Agents for AI DiplomacyZhenyu Guan, Xiangyu Kong, Fangwei Zhong, Yizhou WangNeurIPS 2024 · 48 citations
  3. AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse EnvironmentsZhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong et al.ACL 2025 · 20 citations
  4. Structure Learning-Based Task Decomposition for Reinforcement Learning in Non-stationary EnvironmentsHonguk Woo, Gwangpyo Yoo, Minjong YooAAAI 2022 · 5 citations

Related papers

  1. FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based AgentsChiwei Zhu, Benfeng Xu, Mingxuan Du, Shaohan Wang et al.ACL 2026 · 2 citations
  2. Cognitive Scaffold: From Fluid Context to Crystallized Memory for Long-Horizon DeepResearch AgentsQiuyuan Ai, Zenghuang Fu, Zhaoyang Li, Ping Jiang et al.ACL 2026
  3. MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon AgentsZijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim et al.ICLR 2026 · 223 citations
  4. Context as a Tool: Context Management for Long-Horizon SWE-AgentsShukai Liu, Bo Jiang, Jian Yang, Yizhi Li et al.ACL Findings 2026
  5. A Human-Inspired Reading Agent with Gist Memory of Very Long ContextsKuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John F. Canny et al.ICML 2024 · 106 citations
Dusk over the sea between two cliffs drawn in fine vertical lines