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

Oct 8, 2026cs.AI

TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks

Agents combine reasoning with tools to interact with external systems and complete real-world tasks. Early agents typically interleave reasoning and actions along a single execution chain. On complex tasks, this chain becomes unreliable because growing histories obscure intermediate dependencies and allow early planning errors to propagate. Recursively decomposing a complex task into smaller subtasks offers a natural solution, yet effective decomposition must account for the system's capabilities so that each subtask can be executed by the available tools. In realistic systems, however, tool libraries can be too large to expose in full. Injecting every tool description consumes substantial context while making relevant tools harder to retrieve and useful task boundaries harder to identify. We propose tool-aware recursive decomposition, which organizes tools by functional relationships into a hierarchy of capabilities. During execution, the agent discovers tools on demand and uses the hierarchy to recursively decompose a complex task into a subtask tree whose levels are aligned with the capabilities required at each stage. Experiments on complex real-world tasks show that the proposed method improves end-to-end task success rate by up to 40 percentage points over the compared baselines. The implementation of TaReD is available on GitHub: https://github.com/WeiXiang-Mao/TaReD.

Wei-Xiang Mao, Zhi-Kai Chen, De-Chuan Zhan +1

Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China

Tool-Using Agents Long-Horizon Agent Tasks Task Decomposition

Oct 6, 2026cs.LG

TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery

Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely degrade task performance when applied to agentic models. We trace this failure to two decisions: what to prune and how to recover. For pruning, one-shot importance estimates fail to track how the pruned model adapts. For recovery, offline distillation covers only teacher prefixes, while full-trajectory on-policy distillation causes student errors to compound across turns. In this work, we propose Trajectory-Anchored Pruning (TAP), the first structural pruning framework for reinforcement learning (RL)-trained agents. TAP couples structural pruning with efficient on-policy recovery, anchoring interactions to teacher trajectories while allowing the student to generate each reasoning-action response. A frozen dense teacher supervises the student's response prefixes, addressing within-response training-inference mismatch while preventing student-induced deviations from propagating across training turns. Instead of one-shot pruning, TAP re-scores channels using gradients of the recovery objective on the recovered student, connecting iterative channel selection to the evolving policy. With 60% of FFN channels removed, TAP retains 99.2% and 88.0% of the dense 7B agents' task success rates on ALFWorld and WebShop, respectively, while reducing GPU time per successful task by approximately 22% and 17%. These results demonstrate effective structural compression of long-horizon agents under a limited recovery budget.

Yuanzhe Li, Pengxin Wang, Yuxin Ren +5

University of Arizona · University of Pittsburgh · University of Central Florida

LLM Pruning LLM Inference Acceleration Long-Horizon Agent Tasks On-Policy Distillation

Oct 5, 2026cs.LG

Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents

Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of the same agent on the same task often plateau at substantially different scores, with gaps that persist even after considerable additional compute. Embedding their candidate artifacts by functional similarity provides further evidence that trajectories remain in localized regions of the solution space, which we call idea basins. To help agents escape these basins, we study a simple periodic intervention, fork-and-flush. Our method forks the agent into parallel trajectories, each inheriting the accumulated workspace but starting with a fresh chat context. After running each trajectory for a fixed horizon, the agent continues from the highest-scoring one. Across 13 long-horizon research and engineering tasks, with individual agent runs lasting up to several days, fork-and-flush outperformed the single-run and best-of-N baselines by a relative improvement of 66.0% and 44.4%, respectively, on the min-max normalized average score under an equal compute budget.

Ziyang Cai, Christos Ziakas, Vasilis Kontonis +5

Microsoft Research

Local Search Long-Horizon Agent Tasks Autonomous Experimentation Autonomous Research Agents

Oct 5, 2026cs.LG

Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training

Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon}, the number of trajectory tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improves with longer horizons but saturates: on Terminal-Bench, a 12K-token horizon solves more tasks than 16K (

29\pm0.7

vs.\

26\pm0.8

) while requiring 30% less training time. The horizon also shapes agent behavior: short horizons cause premature termination, intermediate horizons yield productive error recovery, and long horizons induce over-persistence. We analyze this saturation through a bias--complexity bound, in which longer supervision reduces temporal supervision bias but increases finite-sample estimation error from more heterogeneous late-stage histories. Guided by this analysis, we propose \emph{selective long-horizon refinement}, which first trains on short prefixes and then refines only on continuations that are most likely under the warm-start model. It consistently outperforms full long-horizon training. At 16K, it raises successful attempts from

110\pm2.7

to

126\pm2.1

and tasks solved in at least six of eight attempts from

9\pm0.7

to

14\pm0.6

; with half of the long-horizon data, it still reaches

122\pm2.4

while cutting training time by 23%. The gains transfer across benchmarks, from

64\pm2.6

to

73\pm2.1

on Terminal-Bench v2.0 and from

137\pm2.7

to

155\pm2.2

on OpenThoughts-TBLite. For long-horizon supervision, selecting the right trajectories matters more than training on all of them.

Cuong Dang, Hoang Anh Just, Ruoxi Jia

Department of Electrical and Computer Engineering Virginia Tech Blacksburg, VA, USA

Supervised Fine-Tuning Trajectory Generation LLM Agent Training Long-Horizon Agent Tasks Long-Horizon LLM Agents

Oct 2, 2026cs.LG

SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents

Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contributions, while on-policy distillation can lose informative teacher guidance as student-generated histories grow. To address this problem, we introduce SCAD, which organizes interactions into planning and bounded subtask execution, distills execution in local contexts, and refines planning credit through cross-rollout subtask prefix trees, with planning receiving full terminal credit and execution receiving positive terminal credit and teacher guidance. Across all evaluated benchmarks, SCAD improves macro-average accuracy over the strongest training baseline by 4.48 percentage points for text tasks and 4.19 points for multimodal tasks. SCAD effectively combines outcome-based credit assignment with teacher-guided distillation to improve planning and execution in long-horizon agents.

Shangyang Wu, Shuai Zhao, Ziyue Zhu +3

Beijing University of Posts and Telecommunications · Tsinghua University

Hierarchical Planning Step-Level Credit Assignment in RL On-Policy Distillation Long-Horizon Agent Tasks

Oct 1, 2026cs.AI

DAYJOB: A Benchmark for Long-Horizon Professional Work

Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds. We introduce DAYJOB, a benchmark of 130 tasks built by professionals in healthcare (50) and finance (80). The tasks are estimated to take a professional 13.6 hours on average in healthcare and 16.6 in finance. Each task is a containerized Harbor environment with an expert rubric of binary criteria (median 47.5 and 57.5 per task) that an agentic judge applies to the delivered files, and an attempt passes only if it meets every criterion. Across 30 model configurations from 13 developers, the strongest, Claude Opus 5.5, passes 24.7% of healthcare and 23.9% of finance attempts, and the median configuration passes 0.6% and 2.5%. In case studies, agents accept premises that the record contradicts and carry wrong inputs through otherwise consistent analyses. We release all healthcare tasks, 50 of the 80 finance tasks, the evaluation harness, and the leaderboard.

Stephanie Finley, Liudas Panavas, Thomas Mikkelson +12

Surge AI

LLM Agent Evaluation Long-Horizon Agent Tasks Finance Agent Benchmarks

Sep 30, 2026cs.AI

Consistent Plan-Act for Long-Horizon Agentic Tasks

Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agents for structured state assertions and compare their reports programmatically to detect explicit contradictions. Our analyses reveal systematic disagreement about the same task-relevant state facts, a phenomenon we term planner-actor state mismatch. We further find that providing agents with task-relevant state information reduces mismatch and improves coordination and task performance. Based on the systematic analysis of the state mismatch, we propose Consistent Plan-Act (ConPAct), which feeds detected contradictions back to both agents to form consistent state interpretations and fine-tunes them on curated consistent interactions for better coordination. ConPAct improves performance across various environments and model configurations, e.g., increasing MiniGrid success rate from 38.6% to 54.4% with GPT-5.6-sol/terra as planner and actor respectively, demonstrating that state consistency can guide both inference-time correction and coordination training.

Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang +4

School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University · LongCat Team, Meituan +1

Multi-Agent Coordination Long-Horizon Agent Tasks LLM Agent Planning

Sep 29, 2026cs.AI

CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents

For a long-horizon agent, context is the bottleneck: the history is resent with every request, the window caps task length, and reasoning degrades as the history grows. Replacing structured objects with compact retrieval Cards shortens the prompt and keeps the exact originals retrievable, but editing the history can break prefix-cache reuse, and prior recoverable methods time their edits by forecasts of future reuse or by preset intervals. We propose CADOC (Cache-Aware Dynamic Object Context), an online algorithm that replaces structured objects with compact Cards while preserving exact, on-demand retrieval of their original contents. CADOC schedules replacements in batches by balancing accumulated waiting cost against shared cache-reconstruction cost. Its scheduling rule follows from an economic order quantity trade-off, recovers the optimal integer batch under stationary assumptions. Across evaluation, CADOC consistently achieves the lowest aggregate input cost among the compared configurations, which reduces input cost by approximately 40% on average while maintaining task performance close to full context. CADOC thus provides a cost-derived approach to compressible context management, demonstrating that efficient compression depends not only on shortening prompts but also on scheduling edits to preserve cache reuse.

Junjie Yao, Zhangchen Zhou, Zhi-Qin John Xu

School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China. · Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, China.

Cost-Aware Inference Prefix Caching Long-Horizon Agent Tasks LLM Context Management Context Compression

Sep 29, 2026cs.AI

PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval

Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger attention-diverting and cascading failures. To address this, we propose PrecogUI, a pre-cognitive architecture that shifts the paradigm from reactive execution to proactive decision-making. Specifically, we design a Proactive Experience Pool (PEP), which caches recurring anomaly and success patterns as "state-action-result" tuples in a dual-memory repository. Furthermore, we introduce a Proactive Simulation Executor (PSE) that learns to forecast the next symbolic UI layout given a candidate action, enabling early anomaly avoidance and ranking candidate actions by predicted reliability. Finally, a Pre-cognitive Execution Controller (PEC) fuses these priors and predictions, prioritizes handling of foreseen anomalies, and ensures execution robustness through a closed-loop error correction mechanism. For robust evaluation, we develop AutoTraj, an automatic data-generation engine, to construct InterfereBench, a benchmark for long-horizon tasks with strong disturbances. Experiments demonstrate that PrecogUI surpasses state-of-the-art methods on InterfereBench while maintaining competitive performance on public benchmarks. The code will be publicly available.

Bin Kang, Jiarui Ouyang, Li Jiang +2

University of Chinese Academy of Sciences · Harbin Institute of Technology · Shenzhen Loop Area Institute +2

GUI Agents Long-Horizon Agent Evaluation Model-Based Planning Long-Horizon Agent Tasks Memory-Augmented Agents

Sep 28, 2026cs.CL

LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles

GUI agents need long-horizon visual reasoning: they must interpret a changing interface while keeping a multi-step plan viable as earlier actions constrain later ones. Existing benchmarks evaluate grounding, computer use, and game play, but rarely test whether agents stay coherent across long chains of coupled decisions. Long-horizon visual puzzles expose this capability directly: a legal move that looks like progress can make the puzzle unsolvable, and the loss shows only several moves later. We introduce LongPuzzleBench, 114 levels in six puzzle games played through native GUI actions, where one objective can take a human over a thousand actions on persistent boards and dead ends go unannounced. With Native GUI Actions alone, the strongest agents solve most objectives, but success falls sharply on harder, longer boards: seven of ten general-purpose agents solve nothing harder than Medium, and none completes Bolt Unscrew Hard, which a human solves along with every other objective. Code Execution CUA does not close this gap, and its scores mix visual solving with algorithmic search. Controlled diagnostics trace these failures to one limitation that neither rules, state hints, nor failure memory removes: agents judge each move by the visible progress it makes, not by the future options it leaves.

Bingo Zhang, Haochuan Lu, Zongjie Li +3

Vera Praxis · Tencent · The Hong Kong University of Science and Technology +2

GUI Agents Long-Horizon Agent Evaluation AI Agent Benchmarks Visually Grounded Reasoning Long-Horizon Agent Tasks

Sep 28, 2026cs.AI

Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses

Harness evolution improves LLM agents by learning from execution trajectories, but existing experience- and skill-based methods are less effective on long-horizon tasks. As interactions grow, useful evidence can be buried by redundant or outdated context, making context management itself a key bottleneck. We introduce ContextEvo, a framework that learns a context policy from long-horizon trajectories. ContextEvo reconstructs the model-visible context at key decision points, identifies context-related failures, and applies targeted policy updates. Starting from the open-source Pi-agent harness, ContextEvo improves performance across three long-horizon task benchmarks, achieving results comparable to or better than several prominent agent harnesses, including Codex, OpenCode, and OpenClaw. Additional analyses show that fixed or locally evolved context strategies can fall short under long-horizon information pressure, while our methods adapt to the information demands of each environment.

Weiyuan Li, Jinghan Xu, Aili Chen +4

School of Data Science, Fudan University · Shanghai Key Laboratory of Data Science · College of Computer Science and Artificial Intelligence, Fudan University

Agent Harness Optimization Long-Horizon Agent Tasks LLM Context Management Self-Evolving Agents

Sep 28, 2026cs.LG

Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning

Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. Recent work has begun to use reinforcement learning to make memory control part of the policy, often relying on predefined memory tools within domain-specific training environments of relatively short horizons. This setup ties learned memory behavior to environment-specific interfaces that lie outside the base model's pre-training and must be learned from scratch, so even after post-training, agents struggle to use memory in long-horizon tasks. To address these limitations, we introduce Coding Agent Memory Gym (CAMG), a suite of long-horizon agentic-RL environments spanning Shop, Coding, DeepResearch, and AutoResearch. Alongside each environment's native task interface, CAMG provides executable shell access and an episode-persistent workspace, enabling agents to create, revise, search, and reuse files as memory throughout an episode. We also introduce CAMG-RL, which trains a single policy jointly across all four environments with fully asynchronous PPO, learning this file-based memory behavior directly from downstream task reward, and we train CAMG-RL-4B and CAMG-RL-9B from Qwen3.5 models of matching size. On SWE-bench Verified and MLE-bench Lite, CAMG-RL-4B and CAMG-RL-9B are competitive with Qwen3.5-35B-A3B and Qwen3.5-122B-A10B, respectively.

Lirui Luo, Kelong Mao, Heming Xia +10

LLM Agent Memory Persistent Memory for Language Models RL Post-Training Long-Horizon Agent Tasks RL for LLM Agents Memory-Augmented Language Model Agents

Sep 28, 2026cs.CV

Marathoner: Ultra-Long-Horizon Autonomous Intelligence

Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a specific objective. In this paper, we propose Marathoner, an autonomous agentic model possessing the ability of ultra-long-horizon execution. Specifically, we propose a comprehensive post-training pipeline to instill this critical capability into base model. For Ultra-Long-Horizon Task Synthesis, we leverage major release PRs containing 1000+ lines of new code from diverse GitHub repositories as the primary source for synthesizing challenging task-level data. Additionally, we introduce Multi-Task Chaining, which chains multiple generated tasks into a single more challenging task, enabling the synthesis of tasks with frontier-level difficulty. For rejection sampling finetuning, we combine strong teacher model with diverse harnesses to generate trajectories on our synthesized tasks and conduct supervised finetuning on base model with rejection sampled trajectories. For reinforcement learning, cold-started model performs real-world execution through harnesses in independent sandboxes during rollout process, effectively facilitating the acquisition of genuine ultra-long-horizon execution capability. We further propose a novel reward strategy, Later Stage Bonus Reward, which explicitly encourages model to perform meaningful maneuvers during later stages of execution. Through extensive evaluation on 5 benchmarks containing ultra-long-horizon tasks, Marathoner achieves consistent and substantial performance improvements over base model and even surpasses performance of strong proprietary model. Further analysis shows that Marathoner can consistently work for 10+ hours and conduct 1000+ tool calls on highly challenging tasks.

Zhang Ruiyang, Ou Jinpeng, Xie Yifan +4

FIC, University of Macau · Ant Group · Peking University

Long-Horizon Agent Tasks Long-Horizon LLM Agents RL for LLM Agents

Sep 27, 2026cs.LG

QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents

Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model--environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learning (RL) to such executions poses two fundamental challenges: (1) severe execution variance and prolonged rollout delays cause massive GPU idling; and (2) complex non-linear branching generates massive trajectory redundancy, crippling training efficiency. To address these, we presents QwenGyre, an end-to-end framework for xlong-horizon online RL. QwenGyre elastically reallocates GPUs between rollout and training without interrupting live executions, while its trajectory processor reconstructs branching histories, scores partial progress, and deduplicates redundant paths to bound training costs. Scaled to our flagship model, Qwen~3.8 2.4T, with 700K tokens per rollout, QwenGyre yields a 6.0% absolute gain on NL2RepoBench (52.5%

\to

58.5%) in 48 steps. Across our evaluations on diverse domains of training datasets, QwenGyre delivers up to

1.85\times

and

1.78\times

speedups over Colocate and Async, respectively.

Weiqi Wang, Yuxin Zhou, Mouxiang Chen +9

Alibaba Token Hub, Alibaba Group · University of Science and Technology of China · Tsinghua University

Reinforcement Learning Long-Horizon Agent Tasks Long-Horizon LLM Agents RL for LLM Agents

Sep 27, 2026cs.AI

Trajectory Unlearning on LLM-based Agents

Existing large language model (LLM) unlearning has focused primarily on removing specific knowledge, such as harmful facts, private data, or copyrighted content. However, as LLMs are increasingly deployed as autonomous agents, a fundamental yet overlooked problem emerges: beyond suppressing what an agent knows, an agent should not reproduce undesired behaviors through its action trajectories. In this work, we introduce trajectory-level unlearning, a new problem formulation that targets the removal of specific action trajectories in long-horizon agentic tasks, rather than factual knowledge. We identify two fundamental challenges that distinguish trajectory unlearning from knowledge unlearning: (1) our unlearning target is what the agent \emph{does}, not what it \emph{says}; and (2) trajectories are sequentially dependent action sequences that cannot be decomposed into isolated prompt-response pairs without losing inter-step structure. To address these challenges, we propose Group-injected Relative Policy Optimization (GiRPO), which injects forget trajectories into the policy rollout group with penalized rewards and isolates the normalization statistics, yielding a stable and bounded unlearning signal that does not corrupt gradient updates for normal task trajectories. We construct trajectory unlearning benchmarks from two application scenarios, household tasks (ALFWorld) and online shopping (WebShop), and design three complementary metrics for evaluating forgetting quality and model utility. Experiments on ALFWorld and WebShop demonstrate that GiRPO effectively unlearns target trajectories while preserving task success rates, outperforming existing knowledge-unlearning baselines on both forgetting quality and task utility.

Yingdan Shi, Ren Wang

Illinois Institute of Technology, Chicago, USA

Long-Horizon Agent Tasks LLM Unlearning

Sep 27, 2026cs.AI

Raven: The Harness of Harnesses for Composable Agentic Intelligence

As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to specific domains limits the generality of a single harness. The central question thus shifts from how to engineer a stronger harness for one domain to how to autonomously construct specialized harnesses, improve them through experience, and orchestrate them across domains. We introduce Raven, \emph{The Harness of Harnesses}, an open-source multi-agent ecosystem that automatically constructs and evolves modular harnesses for specific models and domains, treating each executable model--harness pair as a composable unit of intelligence. To support an \emph{All-Domain Collaboration Network}, its Host Agent decomposes goals, matches subtasks to specialized agents, coordinates execution dependencies, and integrates results, while a host archive and EverOS preserve experience across tasks and Skill Forge makes that experience available as reusable procedures. Our theory establishes sufficient conditions for such composition to expand reliable task coverage beyond that of the available individual agents under a shared resource budget. On complex and long-horizon tasks, Raven significantly outperforms the state-of-the-art agent systems, pushing the frontier of composable agentic intelligence.

EverMind AI

EverMind AI

LLM Agent Orchestration Agent Harness Optimization Multi-Agent Collaboration Long-Horizon Agent Tasks Agentic AI

Sep 27, 2026cs.CL

Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation

On-policy distillation (OPD) transfers the capabilities of a large language model to a smaller student by providing teacher supervision on the student's own rollouts. In long-horizon agentic tasks, however, uniform token-level matching can allocate supervision poorly: a large local discrepancy need not improve future behavior, while consequential guidance may be beyond the current student's reach or fail to persist without privileged input. We formulate long-horizon OPD as hierarchical supervision allocation and argue that productive guidance lies at the intersection of future utility and current learnability. Crucially, this intersection evolves as the student learns. Based on this principle, we propose LENS-OPD, a coarse-to-fine framework that organizes supervision through Locate, Validate, and Refine. Locate adapts trajectory exposure to the student's evolving competence and proposes a candidate decision for intervention. Validate tests whether teacher guidance at that decision improves the same student's subsequent behavior. Refine internalizes the beneficial guided behavior into the deployable policy and concentrates token-level supervision on decisive teacher-student conflicts within the validated turn. These stages are nested: each finer allocation is conditioned on the coarser decision, rather than being optimized as an independent importance score. Experiments across multiple long-horizon agent benchmarks and student-teacher configurations show that LENS-OPD consistently improves task performance over vanilla OPD and strong curriculum- and selection-based baselines. Our results suggest that effective long-horizon distillation requires teaching at the right depth, the right decision, and the right token.

Yuhao Sun, Binrui Wu, Zhuoer Xu +5

Ant Group · University of Science and Technology of China · Alibaba International Digital Commerce Group +2

On-Policy Distillation Long-Horizon Agent Tasks Long-Horizon LLM Agents

Sep 23, 2026cs.CV

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Long-horizon embodied interaction requires agents to retain and continually update information about the environment as they observe, act, and encounter change. Yet current agents struggle to maintain such memory reliably. Our analysis traces this limitation to four key deficiencies: weak fine-grained visual memory, unreliable dynamic world-state tracking, failing to record world state revealed by interaction outcomes, and limited generalization from prior experience. However, existing benchmarks do not directly assess these memory capabilities during long-horizon embodied interaction. To address this gap, we introduce EmbodiedMemory-Bench (EMem-Bench), comprising 2,554 interactive episodes across four task families. EMem-Bench requires agents to build and update memory from interaction history, then use it to complete a later task by acting in the environment. We further present Embodied-Memorizer (EMem), an external memory system that organizes embodied experience into spatial, event, and scene memories. We also train EMem-8B, an 8B policy that manages and uses these memories. We evaluate a diverse range of open-source and proprietary MLLMs and representative multimodal memory systems. Results show that current models remain weak and uneven across the four challenges. Under matched backbones, EMem achieves the best overall performance among the evaluated memory systems and improves both open-source and proprietary models, while EMem-8B further improves over its backbone. Project page: https://zju-omniai.github.io/EmbodiedMemoryBench/

Lizhou Liang, Xinyu Zhong, Miao Pan +7

Zhejiang University · Central South University · Institute of Software, Chinese Academy of Sciences

Long-Horizon Agent Tasks Embodied AI Memory-Augmented Agents

Sep 17, 2026cs.AI

An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence

Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any context window, any process and any interval at which a person can attend. In this paper, we argue that a long-horizon agent must run continually without forgetting before it can learn continually. This ability lies in the harness around the model rather than in the model itself. We derive seven bottlenecks from the long-horizon setting and answer them with a hierarchical architecture of three parts: (i) levels indexed by time scale, each keeping a bounded file summarising the level below; (ii) a clocked tick as the unit of autonomous action; and (iii) cascaded intelligence, where work is escalated to a more capable model only after failing review. We report on a ten-day campaign in which an agent built on this architecture reproduced a published reinforcement-learning result with a human attending once a day, and show (1) the agent kept the thread across every context reset and session boundary of the campaign, (2) operating knowledge written early changed later behaviour with no change to model weights, and (3) where learned components would enter such a system. Overall, our experience suggests continual learning for these agents needs a substrate outliving every context and process, and the checks the harness already runs are where a learner belongs.

Erik Nijkamp, Anurag Koul, Egor Pakhomov +1

Salesforce AI Research

Cognitive Architectures for AI Agents Continual Learning for LLM Agents Long-Horizon Agent Tasks Long-Horizon LLM Agents Memory-Augmented Language Model Agents

Sep 12, 2026cs.AI

Do Not Restart: Residual Completion for Stateful Agent Handoffs

Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effects, and unfinished obligations. We formulate this as commitment-constrained residual completion and introduce Commitment-Frontier Residual Completion (CFRC). CFRC enforces target-before-proposal, whole-proposal-before-authority, and live-evidence-before-success: it freezes a residual contract from accepted progress, closes the successor continuation into an evidence-linked graph, and admits execution only when the remainder is covered, with live receipts discharging obligations. We establish contract-relative partial correctness, which extends to the original residual request under complete contract construction. Across five environments and two same-provider model pairs, CFRC achieves comparable macro accuracy to strong full-task agents at only 22.0%-34.6% of their inference cost, with additional cross-provider results demonstrating broader transfer.

Runzhi Deng, Yiming Zhong, Fang Zhao +1

Nanjing University · Singapore Management University

LLM Agent Orchestration Runtime Enforcement for AI Agents Long-Horizon Agent Tasks LLM Agent Routing

Sep 10, 2026cs.AI

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containing instructions, scripts, and other resources that help agents perform specific tasks. Agent skills are typically executed by loading their skill instructions into an agent's context and relying on the agent to follow them. As task horizons grow, however, this approach becomes increasingly brittle, because reasoning quality degrades as more information accumulates in the context window. We investigate an alternative approach in which skill packages are instead invoked as subagents. Rather than loading skill instructions into the main context, subagent execution spawns fresh context windows dedicated to solving individual subtasks. We show that subagent execution outperforms agent-skill execution when skill packages expose clear input-output contracts and their instructions encode the procedural knowledge needed to fulfill those contracts. The tradeoff is additional communication overhead, as extra tokens are required to coordinate between the main agent and its subagents. Our results show that the benefit of reusable knowledge depends not only on its content, but also on how it is organized and invoked.

Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +2

Cornell University · Microsoft Research Cambridge

LLM Agent Orchestration Long-Horizon Agent Tasks

Sep 7, 2026cs.AI

From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents

Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the action can change in the meantime. For example, after an agent proposes an 80 GBP refund under a limit of 100, a customer-name change affects only presentation metadata, a new limit of 90 still permits the refund, a limit of 50 invalidates it, and a refund issued by another worker must prevent a duplicate. Standard optimistic concurrency control and version checks can detect that previously read state has changed, but by themselves do not determine whether that change invalidates the pending action's justification. We call any detected version change a version conflict; when that change invalidates the action's justification, it is also a decision conflict. ATR records the explicit, executable conditions that justify a pending action and rechecks only the conditions affected by a change before releasing the external operation. It can retain the action, refresh non-decisive metadata, require replanning, or block execution; a target-side transaction or compare-and-set binds checked state to commit. Across 210,000 controlled executions over 15 mutation cases, ATR matched every developer-specified outcome with no false allows or blocks. In ten durable SQLite checkpoint/resume cells, it evaluated 0.6 conditions per change versus 6.0 for FullScan. At 4,093 recorded reads, ATR took 9.3 microseconds versus 2595.9 microseconds for FullScan. These deterministic results establish controlled feasibility, not production generality or automatic extraction of the required conditions.

Yongjian Lyu, Yang Ren, Ruofei Lai +1

Huawei Technologies Co., Ltd. United Kingdom · Xi’an Jiaotong University Xi’an 710049, China

Tool-Using Agents Runtime Enforcement for AI Agents State Tracking Long-Horizon Agent Tasks

Sep 1, 2026cs.AI

Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions using approximately 14x and 15x fewer input tokens (by reader) and at 5-7x lower cost than a budget-capped single-call reading of the raw trace, with higher accuracy (0.85-0.87 versus 0.48). Because the questions were co-designed with the view schema, we treat the token and cost reduction, conditional on schema coverage, as the transferable result. For the agent, on 120-link sequential-dependency tasks, mechanisms that maintain the task's running statistic in per-step state succeed where full-context prompting fails (30/30 versus 8/30 under a clean protocol, n=30, labeled descriptive owing to benchmark-system co-development); a prompt-level scratchpad matches the fold's accuracy at lower cost, and a two-arm decomposition attributes the fold's accuracy to its deterministic aggregate and its cost advantage to its compactness. The fold's remaining value over cheaper alternatives is deterministic auditability and serving the observer from the same state. We derive eleven candidate requirements for trace folding from observed failures and delimit them with an order-sensitive task family on which the fold ceases to help. Code, benchmarks, a regenerable synthetic corpus, and all workbench traces are released.

Egor Pakhomov, Erik Nijkamp

Salesforce AI Research

Long-Horizon Agent Evaluation AI Agent Monitoring Long-Horizon Agent Tasks

Aug 31, 2026cs.LG

E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation

Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-Commerce Bench, the first open-source benchmark that integrates multi-round counterpart negotiation and dynamic events into a year-long business operation. Over a 365-day year, an LLM agent concurrently runs multiple online stores, researching the market, negotiating with suppliers to source inventory, optimizing sales strategies, fulfilling orders, handling returns, and managing cash flow to maximize its end-of-year total assets. To construct a realistic merchant-side operating environment, the product and supplier data are derived from a real e-commerce platform, while a year-long calendar of promotions, natural disasters, and supply-chain shocks continually reshapes demand. For reproducibility, both sides of the market are deterministic: customer purchases and returns follow a fixed demand model, while a negotiation kernel determines supplier pricing, concessions, and decisions, with an LLM used only to verbalize them. We evaluate 18 frontier models across seven dimensions, including year-end assets, and find that no single model dominates. GPT-5.6 Sol earns the most, growing the 100,000 opening stake into 1,431,425, yet it ranks 16th of 18 on fraud avoidance and trails Fable5 in operational efficiency. Among open-weight models, Qwen3.8-Max-Preview leads with 416,252, 38% above GLM 5.2 (high), and achieves the strongest learning over the horizon, progressively bargaining down prices across repeated orders. Our code is available at https://github.com/QwenLM/E-CommerceBench.

Wei Fan, Xinjie Shen, Xudong Guo +8

1Qwen Team, Alibaba Group · Department of Computer Science and Engineering, HKUST · 2Taobao & Tmall Group, Alibaba Group

Long-Horizon Agent Evaluation AI Agent Benchmarks Long-Horizon Agent Tasks Agentic Commerce

Aug 31, 2026cs.AI

HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving

Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent.

Boyang Mu, Zhiwei Wei, Mugen Peng +1

Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing, China · Hunan Normal University School of Geographic Sciences Changsha, Hunan, China

Multi-Agent Collaboration Remote Sensing Multi-Agent Systems Long-Horizon Agent Tasks Long-Horizon LLM Agents

Aug 31, 2026cs.AI

Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation

Long-horizon physical-world agents must reason over distant goals while grounding decisions in reliable closed-loop behavior. Today's foundation models split these capabilities: vision-language models (VLMs) infer missing information and adapt high-level plans but remain brittle and inefficient at repeated navigation grounding, while navigation foundation models (NFMs) robustly execute semantic goals but operate as bounded episodes without persistent task-level reasoning. We introduce NavMCP, an agentic scaffolding framework that couples a VLM reasoning agent with an NFM executor for long-horizon exploration. The VLM decides what evidence to seek, where to search, and when to stop, while the NFM grounds each semantic sub-goal into closed-loop navigation. Three channels structure their collaboration: intent translates evidence needs into navigation calls, observation converts rollouts into source-grounded trajectory evidence, and memory accumulates findings, negative evidence, and unresolved goals across calls. This design turns isolated navigation rollouts into persistent embodied interaction without retraining either model. On Embodied Question Answering, NavMCP achieves state-of-the-art results on HM-EQA, MT-HM3D, and EXPRESS-Bench. Under matched agent and executor backbones, it outperforms an episodic interface by 14.9 percentage points on HM-EQA. On a Unitree Go2, NavMCP reaches 78.3% success, with its margin over the strongest baseline growing from 10 to 45 points as the task horizon increases. These results demonstrate the potential of scaffolding complementary foundation models into long-horizon physical-world agents.

Zixing Lei, Gengze Zhou, Xiong-Hui Chen +7

Shanghai Jiao Tong University · AIML, Adelaide University · Qwen Team, Alibaba Inc +3

Embodied Navigation Robot Foundation Models Embodied QA Long-Horizon Agent Tasks Memory-Augmented Agents

Aug 26, 2026cs.AI

SKILL.state: Scalable Long-Horizon Agent Skills

Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning traces to an ever-growing conversation history, causing latency degradation and context-poisoning failures over long horizons. We present SKILL. state, a runtime architecture that replaces append-only conversational history with an explicit, mutable execution state. At each execution step, the model receives only the immutable skill specification, the current structured execution state, and the latest observation. Intermediate reasoning is discarded immediately after producing a validated state update, preventing prompt growth with execution history. Across diverse datasets, models, and execution environments, SKILL. state improves task accuracy while substantially reducing cumulative token consumption. Our results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills.

Sanket Badhe, Priyanka Tiwari, Jonghyun Chung

Google LLC · Purdue University

Long-Horizon Agent Tasks Long-Horizon LLM Agents LLM Agent Harnesses

Aug 11, 2026cs.CL

VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?

Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments. Everyday life assistance is different. A task runs for weeks rather than minutes. The world keeps changing while the agent is not being prompted. Many constraints are never stated outright. An agent that merely answers the request in front of it will fail at such a task. What is needed instead is an agent that stays proactive and consistent. It decides on its own when to act, when to ask, and when to stay silent. It notices changes that nobody announced. It keeps one plan coherent from the first day to the last. No current benchmark measures this. We introduce VibeLifeBench, a benchmark of 200 long-horizon tasks across ten everyday-life domains. Each task is a scripted multi-week timeline in a simulated world of 22 mock services. The world advances on its own clock, and many of its changes are silent, so only an agent that re-inspects the world discovers them. Every task is graded by fine-grained, weighted checks that read only what the agent actually left behind, covering the end state, the timeliness of its actions, and whether it upheld the implicit constraints. We evaluate seven frontier models. All of them score low, which shows how far current agents are from assisting with real life. We will open-source all tasks, environments, and the evaluation framework.

Xiaohongshu Inc

Xiaohongshu Dots Studio · Evolvent AI

Long-Horizon Agent Evaluation AI Agent Benchmarks Proactive Assistance Long-Horizon Agent Tasks Agentic AI Personal AI Agents

Aug 11, 2026cs.SE

Persistent Recursive Worlds Enable Autonomous Software Evolution

Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent.

Beichen Huang, Zhenyu Liang, Bowen Zheng +1

Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University Hong Kong SAR, China

Automated Software Engineering Repository-Level Code Generation Long-Horizon Agent Tasks Self-Evolving Agents

Aug 11, 2026cs.LG

Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks

Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a natural fit for this setting, but multi-turn on-policy rollouts create long contexts, while model-specific attention layers may require custom masks and learned sink normalization. We present SINKFLEX-RL, a modular training system for RL in dual-control tool-use environments. The system combines a Gymnasium-compatible environment wrapper, a VERL-style rollout dataflow, group-relative policy optimization without a separate value model, and a sink-aware FlexAttention path designed to preserve model-specific sink scaling under causal and sliding-window masks. In a preliminary Tau2Bench retail run, validation reward (mean@1) rises from 0.25 early in training to

0.44

later in the observed training window, while training-score and trajectory-reward proxies also trend upward. In a fixed-configuration memory benchmark, the optimized attention path reduces peak VRAM from 28.06GB to 22.52GB at 4096 tokens, a

19.7\%

reduction, and runs the measured 8192-token configuration using

25.53

~GB where the eager baseline runs out of memory. These results illustrate the value of integrating environment interfaces, RL dataflow, and attention-kernel design for memory-feasible long-horizon agent training.

Zelei Cheng, Amritansh Mishra, Sambit Sahu +1

AI Foundations, Capital One

Efficient Attention Long-Horizon Agent Tasks RL for LLM Agents RL for Tool Use