Long-Horizon LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

60 papers in the last four weeks, up 161% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 297

All topics

Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents
Sep 29, 2026Qi Zhou, Yuanfan LiCredit Assignment in RL Long-Horizon LLM Agents
Xi’an Jiaotong University
GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements
Sep 29, 2026Zhibang Yang, Xinke Jiang, Yuxuan Liu +9LLM Agent Memory Long-Horizon LLM Agents
National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Sep 29, 2026Guanghui Min, Liang Wu, Mingjia Shi +4Counterfactual Evaluation LLM Agent Evaluation
University of Virginia · Nokia
Continuous Context Management
Sep 28, 2026William Hoy, Jingxuan Fan, Nurcin Celik +1Context Distillation Long-Horizon LLM Agents
University of Miami · Harvard University
SRHarness: A Harness for Agentic Symbolic Regression
Sep 28, 2026Zihan Yu, Shixuan Zhou, Hao Huang +2Long-Horizon LLM Agents Large Language Model-Guided Scientific Discovery
Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China · College of AI, Tsinghua University, Beijing, China · Department of Earth System Science, Tsinghua University, Beijing, China
Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation
Sep 28, 2026Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu +5Cost-Aware Inference Inference-Time Scaling
Meituan LongCat Team · Zhejiang University · Westlake University +2
Research-Native by Construction: Minimal Nodes, Re-verifiable Workflows, and Compounding Memory for Long-Horizon Scientific Agents
Sep 28, 2026Di Wang, Yu Liu, Bing Cui +5Runtime Enforcement for AI Agents Scientific Reproducibility
IdeaHorizon Team
GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents
Sep 28, 2026Haodong Zhu, Yangyang Ren, Changbai Li +4Credit Assignment in RL Step-Level Credit Assignment in RL
Beihang University · Zhongguancun Academy · Communication University of China +1
RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents
Sep 28, 2026Hao Li, Hangfan Zhang, Zhiyao Cui +5Cost-Aware Inference LLM Agent Workflow Optimization
Shanghai Artificial Intelligence Laboratory · Northwestern Polytechnical University
FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management
Sep 28, 2026Peiyu ZangLong-Horizon Agent Evaluation AI Agent Benchmarks
School of Mathematical Sciences, Beijing Normal University · CoRe Lab, Institute for Artificial Intelligence, Peking University
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Sep 28, 2026Minghao Li, Bangyan Li, Zifan Wang +5LLM Agent Memory Long-Horizon LLM Agents
Ant International, Ant Group
SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning
Sep 28, 2026Jaeho Jung, Sung Hoon JungLLM Agents Long-Horizon LLM Agents
Independent Researcher Seoul, Republic of Korea · Department of Applied Artificial Intelligence Hansung University Seoul, Republic of Korea
Marathoner: Ultra-Long-Horizon Autonomous Intelligence
Sep 28, 2026Zhang Ruiyang, Ou Jinpeng, Xie Yifan +4Long-Horizon Agent Tasks Long-Horizon LLM Agents
FIC, University of Macau · Ant Group · Peking University
StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents
Sep 28, 2026Wenle Liao, Zhao Wang, Jingchao Zhang +3LLM Agent Verification Graph-Based Agent Memory
Gaoling School of Artificial Intelligence Renmin University of China
From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
Sep 28, 2026Mingxi Zou, Langzhang Liang, Zhuo Wang +3Adversarial Attacks Agent Memory Poisoning
Shanghai Academy of AI for Science (SAIS) · Fudan University · Monash University
HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents
Sep 27, 2026Tingsong Xiao, Nithish Balachandar Moudhgalya, Chandrayee Basu +5Monte Carlo Tree Search Long-Horizon LLM Agents
University of Florida · Amazon
When Consent Outlives Context: Residual Authority Replay in Long-Lived Agents
Sep 27, 2026Zhihao Zhang, Chao Wang, Rujia Li +3LLM Agent Security Prompt Injection Attacks on AI Agents
Worcester Polytechnic Institute · Tsinghua University · Independent Researcher
When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
Sep 27, 2026Janvijay Singh, Vaishnavi Shrivastava, Dilek Hakkani-Tur +2Long-Horizon Agent Evaluation AI Agent Benchmarks
University of Illinois Urbana-Champaign · Microsoft Research AI Frontiers
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
Sep 27, 2026Weiqi Wang, Yuxin Zhou, Mouxiang Chen +9Reinforcement Learning Long-Horizon Agent Tasks
Alibaba Token Hub, Alibaba Group · University of Science and Technology of China · Tsinghua University
Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation
Sep 27, 2026Yuhao Sun, Binrui Wu, Zhuoer Xu +5On-Policy Distillation Long-Horizon Agent Tasks
Ant Group · University of Science and Technology of China · Alibaba International Digital Commerce Group +2
Agentic Multi-Turn Reasoning: A Fairness Approach
Sep 27, 2026Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill +3Preference Optimization Agentic Reasoning
CVIU Lab, University of Arkansas, USA · Dep. of Physics, University of Arkansas, USA · Dep. of Geosciences, University of Arkansas, USA +1
Adaptive Consistency Graph for Long-Horizon Agents
Sep 26, 2026Jiecong Wang, Hao Peng, Zhanyi WangLong-Horizon Agent Evaluation Graph-Based Agent Memory
Beihang University · QI-ANXIN GROUP
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
Sep 25, 2026Dongsheng Xiao, Zeyuan Wang, Xuzhe Xia +2Overthinking in Language Models LLM Agents
Queensland Brain Institute, The University of Queensland, Brisbane, Queensland, Australia · School of Cyber Security, Northwestern Polytechnical University, Xi'an, Shaanxi, China · Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, British Columbia, Canada +2
When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
Sep 24, 2026Mingxuan Wang, Fei Luo, Bo Wang +6Long-Context Modeling Long-Horizon LLM Agents
TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Sep 24, 2026Xingyu Wu, Yuchen Yan, Zhengxi Lu +9Long-Horizon LLM Agents RL for LLM Agents
Zhejiang University · Tencent
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Sep 23, 2026Shuang Sun, Guoxin Chen, Fanzhe Meng +6LLM World Models World Models
Gaoling School of Artificial Intelligence, Renmin University of China
Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents
Sep 23, 2026Jiaxing Li, Lei Song, Rui Dong +1Graph-Based Agent Memory Long-Horizon LLM Agents
School of Computer Science and Engineering, Southeast University, Nanjing, China
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Sep 23, 2026Xinjie Shen, Wei Fan, Xudong Guo +5Agentic RL Reinforcement Learning
Georgia Institute of Technology · Alibaba Token Foundry, Alibaba Group
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
Sep 22, 2026Zhening Li, Joshua Liu, Mateja Vukelic +7LLM Agent Memory LLM Agent Self-Improvement
MIT CSAIL · Independent Researcher
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
Sep 22, 2026Trang Nguyen, Eulrang Cho, Bingqing Chen +1Continual Learning for LLM Agents Test-Time Scaling
Carnegie Mellon University · Bosch Center for AI

Sep 29, 2026, cs.AIJ/K move · Enter open · S save

Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents

Qi Zhou, Yuanfan Li

Xi’an Jiaotong University

Credit Assignment in RL Long-Horizon LLM Agents Policy Learning RL for LLM Agents

Open paper AskPDF arXiv

Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Existing group-based methods such as GRPO and GiGPO alleviate this issue by comparing rollout returns or repeated anchor states, but they still fail when the compared returns have no variation. We identify this failure mode as zero-credit failure: during early training, many failed rollouts contain useful prefixes, yet existing methods assign them no task-discriminative advantage. To address this issue, we propose Milestone Viability Potential Policy Optimization (MVPO), a potential-routed policy optimization algorithm that learns from viable failure prefixes. MVPO estimates prefix potential over Union-Find viability regions, repairs zero-credit groups with potential-difference advantages, and attenuates the potential branch according to relative performance progress. Experiments with Qwen2.5-1.5B-Instruct show that MVPO outperforms eight strong baselines, including GRPO and GiGPO. Under the same training length, MVPO improves over the GiGPO baseline by +4.4 success points on ALFWorld and +5.3 on WebShop, while adding only 0.16%-0.20% advantage-construction overhead.

Momentum

Related topics

Latest papers 297