Long-Horizon LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Long-horizon LLM agents are systems designed to pursue goals through many connected actions, often while using tools and responding to changing information. Common approaches include hierarchical planning and subgoals, reinforcement learning with step-level or milestone rewards, persistent memory and context compression, and harnesses that verify actions and recover from errors. Researchers evaluate them in interactive settings such as ALFWorld, WebShop, ScienceWorld, WebArena, software-engineering benchmarks, and deep-research tasks. A central challenge is making performance reliable over time: errors and lost constraints can compound, while memory, verification, and extra computation can improve success but add cost or introduce new failure modes.

Latest papers

451 papers92 papers in the last four weeks, up 56% on the four weeks before. 0.5% of all new papers.

Mar 16, 2026

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.

MiroMind Team, S. Bai, L. Bing +41

Autonomous Research Agents Long-Horizon LLM Agents Agentic Reasoning LLM Agent Reliability Reasoning Verification

Mar 15, 2026

Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective

Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into where failures arise. We propose a hierarchical planning framework to analyze web agents across three layers (i.e., high-level planning, low-level execution, and replanning), enabling process-based evaluation of reasoning, grounding, and recovery. Our experiments show that structured Planning Domain Definition Language (PDDL) plans produce more concise and goal-directed strategies than natural language (NL) plans, but low-level execution remains the dominant bottleneck. These results indicate that improving perceptual grounding and adaptive control, not only high-level reasoning, is critical for achieving human-level reliability. This hierarchical perspective provides a principled foundation for diagnosing and advancing LLM web agents.

Mohamed Aghzal, Gregory J. Stein, Ziyu Yao

Department of Computer Science, George Mason University

Web Agents LLM Agent Reliability Long-Horizon LLM Agents LLM Agent Planning LLM Agent Evaluation

Mar 13, 2026

StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context

Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context windows, retrieval-augmented generation, summarization, or static documentation -- treat memory as static storage and fail to preserve decision-relevant state under long-running, multi-session tasks. We introduce StatePlane, a model-agnostic cognitive state plane that governs the formation, evolution, retrieval, and decay of episodic, semantic, and procedural state for AI systems operating under bounded context. Grounded in cognitive psychology and systems design, StatePlane formalizes episodic segmentation, selective encoding via information-theoretic constraints, goal-conditioned retrieval with intent routing, reconstructive state synthesis, and adaptive forgetting. We present a formal state model, KV-aware algorithms, security and governance mechanisms including write-path anti-poisoning, enterprise integration pathways, and an evaluation framework with six domain-specific benchmarks. StatePlane demonstrates that long-horizon intelligence can be achieved without expanding context windows or retraining models.

Sasank Annapureddy, John Mulcahy, Anjaneya Prasad Thamatani

LLM Context Management Persistent Memory for Language Models Long-Horizon LLM Agents Memory-Augmented Language Models Cognitive Architectures for AI Agents

Mar 12, 2026

BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based planners are stateless and reactive, operating without persistent memory and therefore repeating errors and struggling with spatial or temporal dependencies. We propose BrainMem(Brain-Inspired Evolving Memory), a training-free hierarchical memory system that equips embodied agents with working, episodic, and semantic memory inspired by human cognition. BrainMem continuously transforms interaction histories into structured knowledge graphs and distilled symbolic guidelines, enabling planners to retrieve, reason over, and adapt behaviors from past experience without any model fine-tuning or additional training. This plug-and-play design integrates seamlessly with arbitrary multi-modal LLMs and greatly reduces reliance on task-specific prompt engineering. Extensive experiments on four representative benchmarks, including EB-ALFRED, EB-Navigation, EB-Manipulation, and EB-Habitat, demonstrate that BrainMem significantly enhances task success rates across diverse models and difficulty subsets, with the largest gains observed on long-horizon and spatially complex tasks. These results highlight evolving memory as a promising and scalable mechanism for generalizable embodied intelligence.

Xiaoyu Ma, Lianyu Hu, Wenbing Tang +4

Nanyang Technological University, Singapore · Tianjin University, Tianjin, China

Long-Term Memory for Embodied Agents Memory-Augmented Language Model Agents Large Language Model-Based Robot Planning Long-Horizon LLM Agents Graph-Based Agent Memory

Mar 12, 2026

From Control to Foresight: Simulation as a New Paradigm for Human-Agent Collaboration

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate risks, without visibility into subsequent consequences. This forces users to mentally simulate long-term effects, a cognitively demanding and often inaccurate process. Users have control over individual steps but lack the foresight to make informed decisions. We argue that effective collaboration requires foresight, not just control. We propose simulation-in-the-loop, an interaction paradigm that enables users and agents to explore simulated future trajectories before committing to decisions. Simulation transforms intervention from reactive guesswork into informed exploration, while helping users discover latent constraints and preferences along the way. This perspective paper characterizes the limitations of current paradigms, introduces a conceptual framework for simulation-based collaboration, and illustrates its potential through concrete human-agent collaboration scenarios.

Gaole He, Brian Y. Lim

National University of Singapore, Singapore

Human-AI Collaboration Human-in-the-Loop AI Long-Horizon LLM Agents

Mar 10, 2026

Deep Tabular Research via Continual Experience-Driven Execution

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.

Junnan Dong, Chuang Zhou, Zheng Yuan +7

Tencent Youtu Lab · Ruijin Hospital, Shanghai Jiaotong University

Table QA Long-Horizon LLM Agents Agentic Reasoning

Mar 8, 2026

DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation

Large language model-based deep research agents have been increasingly popular for addressing long-horizon information-seeking tasks, but they often incur high end-to-end latency due to extensive reasoning and frequent tool use. Speculation frameworks aim to reduce latency by overlapping action execution with reasoning; however, existing approaches typically rely on uniform speculation strategies and strict action matching, which limits inference speedups and robustness. In this work, we revisit the speculate-verify paradigm for deep research agents through the lens of action heterogeneity. We show that Search and Visit actions exhibit fundamentally different reasoning and model capacity requirements: entropy-based analysis reveals that Search decisions have higher uncertainty and benefit significantly from explicit reasoning, whereas Visit decisions have lower entropy and depend primarily on model capacity. Motivated by this dual-process characteristic, we propose DualSpec, a heterogeneous speculation framework equipped with a lightweight, confidence-based semantic verifier. Experiments across multiple models and benchmarks demonstrate that DualSpec achieves up to 3.28

\times

end-to-end speedup while maintaining accuracy comparable to fully reasoning agents.

Shuzhang Zhong, Baotong Lu, Qi Chen +3

Peking University, Beijing, China · Microsoft Research · Microsoft

Deep Research Agents LLM Inference Acceleration Long-Horizon LLM Agents LLM Agent Verification

Mar 7, 2026

Hindsight Credit Assignment for Long-Horizon LLM Agents

Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two fundamental bottlenecks: inaccurate step-level Q-value estimation and misaligned value baselines for intermediate states. To address these limitations, we introduce HCAPO, the first framework to integrate hindsight credit assignment into LLM agents. HCAPO leverages the LLM itself as a post-hoc critic to refine step-level Q-values through hindsight reasoning. Furthermore, HCAPO's multi-scale advantage mechanism effectively supplements the inaccurate value baselines at critical decision states. Evaluations across three challenging benchmarks, including WebShop and ALFWorld, demonstrate that HCAPO consistently outperforms state-of-the-art RL methods. Notably, HCAPO achieves a 7.7% improvement in success rate on WebShop and a 13.8% on ALFWorld over GRPO using the Qwen2.5-7B-Instruct model. These results indicate that HCAPO significantly enhances exploration efficiency, promotes concise decision-making, and ensures scalability in complex, long-horizon tasks.

Hui-Ze Tan, Xiao-Wen Yang, Hao Chen +7

State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · FiT, Tencent, Shenzhen, China +2

Credit Assignment in RL Long-Horizon LLM Agents RL for LLM Agents Step-Level Credit Assignment in RL

Mar 5, 2026

STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

Existing LLM-based web agents struggle on complex, long-horizon tasks due to limited in-context memory, weak planning abilities, and greedy behaviors that lead to premature termination. To address these challenges, we propose \SA{}, a hierarchical planning framework that interleaves planning and execution via dynamic

\ANDOR

trees. The framework separates structural planning from LLM-based reasoning, enabling principled error recovery through node repair, systematic exploration of alternatives via OR nodes, and modular plans that can facilitate human intervention. On WebArena (630 tasks), \SA{} achieves a

\sim

53% success rate vs.\

\sim

46% for AgentOccam, and on complex multi-constraint Amazon shopping tasks, gains reach 10% over the strongest baseline.

ELita Lobo, Xu Chen, Jingjing Meng +5

University of Massachusetts Amherst · Amazon · Virginia Commonwealth University +1

LLM Agent Planning Long-Horizon LLM Agents Web Agents

Mar 5, 2026

HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel

Sequential LLM agents fail on long-horizon planning with hard constraints like budgets and diversity requirements. As planning progresses and context grows, these agents drift from global constraints. We propose HiMAP-Travel, a hierarchical multi-agent framework that splits planning into strategic coordination and parallel day-level execution. A Coordinator allocates resources across days, while Day Executors plan independently in parallel. Three key mechanisms enable this: a transactional monitor enforcing budget and uniqueness constraints across parallel agents, a bargaining protocol allowing agents to reject infeasible sub-goals and trigger re-planning, and a single policy trained with GRPO that powers all agents through role conditioning. On TravelPlanner, HiMAP-Travel with Qwen3-8B achieves 52.78% validation and 52.65% test Final Pass Rate (FPR). In a controlled comparison with identical model, training, and tools, it outperforms the sequential DeepTravel baseline by +8.67~~pp. It also surpasses ATLAS by +17.65~~pp and MTP by +10.0~pp. On FlexTravelBench multi-turn scenarios, it achieves 44.34% (2-turn) and 37.42% (3-turn) FPR while reducing latency 2.5x through parallelization.

The Viet Bui, Wenjun Li, Yong Liu

Singapore Management University

Travel Planning Long-Horizon LLM Agents Multi-Agent Planning Multi-Agent Coordination

Mar 4, 2026

Mozi: Governed Autonomy for Drug Discovery LLM Agents

Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist.

He Cao, Siyu Liu, Fan Zhang +7

AI Agents for Scientific Discovery LLM Agent Orchestration Long-Horizon LLM Agents AI Agent Governance Drug Discovery

Mar 3, 2026

VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning

Large models are increasingly becoming autonomous agents that interact with real-world environments and use external tools to augment their static capabilities. However, most recent progress has focused on text-only large language models, which are limited to a single modality and therefore have narrower application scenarios. On the other hand, multimodal large models, while offering stronger perceptual capabilities, remain limited to static knowledge and lack the ability to access and leverage up-to-date web information. In this paper, we propose VSearcher, turning static multimodal model into multimodal search agent capable of long-horizon, multi-turn tool use in real-world web environments, including text search, image search, and web browsing, via reinforcement learning. Specifically, we introduce Iterative Injection Data Synthesis pipeline to generate large-scale, complex multimodal QA questions, which are further filtered with comprehensive metrics to ensure high quality and sufficient difficulty. We then adopt an SFT-then-RL training pipeline to turn base multimodal models to agent capable of multi-turn tool calling in real-world web environments. Besides, we propose a multimodal search benchmark MM-SearchExam dedicated to evaluating search capabilities of multimodal search agents, which proves highly challenging for recent proprietary models. Extensive evaluations across multiple multimodal search benchmarks reveal effectiveness of our method. VSearcher achieves superior performance compared to recent multimodal search agents and even surpasses several proprietary models on multimodal web search tasks.

Ruiyang Zhang, Qianguo Sun, Chao Song +2

FST and ICI, University of Macau, China · IDEA

Multimodal Search Agents Multimodal Tool Use Multimodal IR Long-Horizon LLM Agents Multimodal Model Evaluation RL for LLM Agents

Mar 1, 2026

Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI

What if accessing the web did not require a screen, a stable desk, or even free hands? For people navigating crowded cities, living with low vision, or experiencing cognitive overload, smart glasses coupled with AI agents could turn the web into an always-on assistive layer over daily life. We present Egocentric Co-Pilot, a web-native neuro-symbolic framework that runs on smart glasses and uses a Large Language Model (LLM) to orchestrate a toolbox of perception, reasoning, and web tools. An egocentric reasoning core combines Temporal Chain-of-Thought with Hierarchical Context Compression to support long-horizon question answering and decision support over continuous first-person video, far beyond a single model's context window. Additionally, a lightweight multimodal intent layer maps noisy speech and gaze into structured commands. We further implement and evaluate a cloud-native WebRTC pipeline integrating streaming speech, video, and control messages into a unified channel for smart glasses and browsers. In parallel, we deploy an on-premise WebSocket baseline, exposing concrete trade-offs between local inference and cloud offloading in terms of latency, mobility, and resource use. Experiments on Egolife and HD-EPIC demonstrate competitive or state-of-the-art egocentric QA performance, and a human-in-the-loop study on smart glasses shows higher task completion and user satisfaction than leading commercial baselines. Taken together, these results indicate that web-connected egocentric co-pilots can be a practical path toward more accessible, context-aware assistance in everyday life. By grounding operation in web-native communication primitives and modular, auditable tool use, Egocentric Co-Pilot offers a concrete blueprint for assistive, always-on web agents that support education, accessibility, and social inclusion for people who may benefit most from contextual, egocentric AI.

Sicheng Yang, Yukai Huang, Weitong Cai +8

Shenzhen International Graduate School Tsinghua University Shenzhen, China · Independent Researcher London, United Kingdom · Queen Mary University of London London, United Kingdom +2

Web Agents Tool-Using Vision-Language Agents Long-Horizon LLM Agents Egocentric Video QA

Mar 1, 2026

HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive policies, where high-level reasoning and low-level actions are generated within a single token sequence, leading to inefficient exploration and severe error propagation over extended trajectories. In this work, we propose HiMAC, a hierarchical agentic RL framework that explicitly decomposes long-horizon decision-making into macro-level planning and micro-level execution. HiMAC models reasoning as a structured blueprint generation process followed by goal-conditioned action execution, enabling robust long-horizon planning within LLM-based agents. To train this hierarchy efficiently, we introduce a critic-free hierarchical policy optimization paradigm that extends group-based reinforcement learning to bi-level structures through hierarchical relative advantage estimation. Furthermore, we propose an iterative co-evolution training strategy that alternates between planner exploration and executor adaptation, mitigating the non-stationarity inherent in hierarchical learning. Extensive experiments on ALFWorld, WebShop, and Sokoban demonstrate that HiMAC consistently outperforms strong prompting and reinforcement learning baselines, achieving state-of-the-art performance and substantially improved sample efficiency across both text-based and visually grounded environments. Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.

Hongbo Jin, Rongpeng Zhu, Jiayu Ding +2

School of Electronic and Computer Engineering, Peking University

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

Feb 28, 2026

M $^2$ : Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on extensive data collection and model training, yet still struggle with high computational costs and insufficient reasoning capabilities when facing complex, long-horizon scenarios. To address this, we propose M

^2

, a training-free, memory-augmented framework designed to optimize context efficiency and decision-making robustness. Our approach incorporates a dual-tier memory mechanism that synergizes Dynamic Trajectory Summarization (Internal Memory) to compress verbose interaction history into concise state updates, and Insight Retrieval Augmentation (External Memory) to guide the agent with actionable guidelines retrieved from an offline insight bank. Extensive evaluations across WebVoyager and OnlineMind2Web demonstrate that M

^2

consistently surpasses baselines, yielding up to a 19.6% success rate increase and 58.7% token reduction for Qwen3-VL-32B, while proprietary models like Claude achieve accuracy gains up to 12.5% alongside significantly lower computational overhead.

Dawei Yan, Haokui Zhang, Guangda Huzhang +8

Northwestern Polytechnical University, Xi’an, China · AI Business, Alibaba Group, Hangzhou, China · Xi’an University of Architecture and Technology, Xi’an, China +1

Long-Horizon LLM Agents Web Agents Memory-Augmented Language Model Agents Retrieval-Augmented ICL

Feb 27, 2026

PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents

Large language model (LLM) agents typically rely on reactive decision-making paradigms such as ReAct, selecting actions conditioned on growing execution histories. While effective for short tasks, these approaches often lead to redundant tool usage, unstable reasoning, and high token consumption in complex long-horizon tasks involving branching, iteration, or multi-tool coordination. To address these limitations, this paper introduces PseudoAct, a novel framework for flexible planning and action control in LLM agents through pseudocode synthesis. Leveraging the ability of LLMs to express task-solving strategies as code, PseudoAct synthesizes a structured pseudocode plan that decomposes a task into subtasks and explicitly encodes control flow, including sequencing, conditionals, loops, parallel composition, and combinations of these logic primitives. Actions are then executed by following this global plan, making the decision logic explicit and temporally coherent. This design reduces redundant actions, prevents infinite loops, and avoids uninformative alternative exploration, enabling consistent and efficient long-horizon decision-making. Experiments on benchmark datasets show that our method significantly outperforms existing reactive agent approaches, achieving a 20.93% absolute gain in success rate on FEVER and setting a new state-of-the-art on HotpotQA.

Yihan, Wen, Xin Chen

Logon · Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA

LLM Agent Planning Long-Horizon LLM Agents

Feb 26, 2026

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving.

Zhaochen Su, Jincheng Gao, Hangyu Guo +10

Hong Kong University of Science and Technology · University of North Carolina at Chapel Hill · Zhejiang University +1

Multimodal Agent Evaluation AI Agent Benchmarks Tool-Using Vision-Language Agents Multimodal Agents Multimodal Tool Use Long-Horizon LLM Agents

Feb 26, 2026

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent

Hao Zheng, Guozhao Mo, Xinru Yan +7

Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

Agentic AI LLM Agents LLM Self-Refinement Long-Horizon LLM Agents

Feb 26, 2026

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains challenging. In this work, we propose Search More, Think Less (SMTL), a framework for long-horizon agentic search that targets both efficiency and generalization. SMTL replaces sequential reasoning with parallel evidence acquisition, enabling efficient context management under constrained context budgets. To support generalization across task types, we further introduce a unified data synthesis pipeline that constructs search tasks spanning both deterministic question answering and open-ended research scenarios with task appropriate evaluation metrics. We train an end-to-end agent using supervised fine-tuning and reinforcement learning, achieving strong and often state of the art performance across benchmarks including BrowseComp (48.6%), GAIA (75.7%), Xbench (82.0%), and DeepResearch Bench (45.9%). Compared to Mirothinker-v1.0, SMTL with maximum 100 interaction steps reduces the average number of reasoning steps on BrowseComp by 70.7%, while improving accuracy.

Qianben Chen, Tianrui Qin, King Zhu +21

Agentic Search Long-Horizon LLM Agents Autonomous Research Agents LLM Agent Training Long-Horizon Agent Evaluation

Feb 25, 2026

Structurally Aligned Subtask-Level Memory for Software Engineering Agents

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning. However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval. We empirically demonstrate that instance-level memory suffers from a fundamental granularity mismatch, resulting in misguided retrieval when tasks with similar surface descriptions require distinct reasoning logic at specific stages. To address this, we propose Structurally Aligned Subtask-Level Memory, a method that aligns memory storage, retrieval, and updating with the agent's functional decomposition. Extensive experiments on SWE-bench Verified demonstrate that our method consistently outperforms both vanilla agents and strong instance-level memory baselines across diverse backbones, improving mean Pass@1 over the vanilla agent by +4.7 pp on average (e.g., +6.8 pp on Gemini 2.5 Pro). Performance gains grow with more interaction steps, showing that leveraging past experience benefits long-horizon reasoning in complex software engineering tasks.

Kangning Shen, Jingyuan Zhang, Chenxi Sun +2

Kuaishou Technology, Beijing, China

LLM Agent Memory Agent Memory Software Engineering Agents Long-Horizon LLM Agents

Feb 24, 2026

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: reflection-in-action, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and reflection-on-action, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead. Qualitative analyses further highlight behavioral correction through reflection.

Yining Hong, Huang Huang, Manling Li +4

Stanford University · Northwestern University

Large Language Model-Based Robot Planning LLM Agent Planning Long-Horizon LLM Agents Embodied Reasoning Test-Time Training

Feb 22, 2026

Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks

Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every well-defined tool-use task imposes a canonical solution path (i.e., a convergent set of tool invocations shared across successful runs) and agent success depends critically on whether a trajectory stays within this path's operating envelope. We establish this causally using a natural experiment that holds model capability and task difficulty fixed by construction. We analyze trajectories from the Toolathlon benchmark: 22 frontier models each attempt 108 real-world tool-use tasks across 3 independent runs, yielding 515 model

\times

task units where the same model succeeds on some runs and fails on others due to LLM sampling stochasticity alone. Within these units, successful runs adhere significantly more closely to the canonical solution path than failed runs (

+

0.060 Jaccard,

p<0.0001

,

n=488

units, 95% CI [+0.043, +0.077]). This result survives six robustness checks including cross-model-family leave-one-out validation. Critically, the causal mechanism is gradual and self-reinforcing: the adherence gap is statistically indistinguishable from zero through the first 50% of the trajectory, ruling out early-branching selection bias, and each off-canonical tool call raises the probability that the next call is also off-canonical by 22.7 percentage points (

\hatβ=+0.227

,

p<0.0001

), more than doubling the baseline rate. These findings imply that agent reliability cannot be improved by capability scaling alone, but offer a highly actionable intervention: a simple monitor that restarts the bottom tercile of runs based on mid-trajectory canonical adherence lifts success rates by

+

8.8 percentage points among intervened runs.

Wilson Y. Lee

Independent Researcher United States

Agent Failure Analysis LLM Agent Reliability Long-Horizon LLM Agents

Feb 20, 2026

Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems

Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for Orchestration), a runtime scheduling layer that optimizes computational allocation under fixed budgets by operationalizing temporal-affective signals. Instead of modifying model weights, APEMO detects trajectory instability through behavioral proxies and targets repairs at critical segments, such as peak moments and endings. Evaluation across multi-agent simulations and LLM-based planner--executor flows demonstrates that APEMO consistently enhances trajectory-level quality and reuse probability over structural orchestrators. Our results reframe alignment as a temporal control problem, offering a resilient engineering pathway for the development of long-horizon agentic systems.

Hanjing Shi, Dominic DiFranzo

Lehigh University, Bethlehem, Pennsylvania, USA

Long-Horizon LLM Agents LLM Agent Workflow Optimization Multi-Agent Orchestration Inference-Time Language Model Alignment

Feb 19, 2026

KLong: Training LLM Agent for Extremely Long-horizon Tasks

This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via progressive RL training. Specifically, we first activate basic agentic abilities of a base model with a comprehensive SFT recipe. Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics. Using this pipeline, we build thousands of long-horizon trajectories distilled from Claude 4.5 Sonnet (Thinking). To train with these extremely long trajectories, we propose a new trajectory-splitting SFT, which preserves early context, progressively truncates later context, and maintains overlap between sub-trajectories. In addition, to further improve long-horizon task-solving capability, we propose a novel progressive RL, which schedules training into multiple stages with progressively extended timeouts. Experiments demonstrate the superiority and generalization of KLong, as shown in Figure 1. Notably, our proposed KLong (106B) surpasses Kimi K2 Thinking (1T) by 11.28% on PaperBench, and the performance improvement generalizes to other coding benchmarks like SWE-bench Verified and MLE-bench.

Yue Liu

NUS

LLM Agent Training Long-Horizon Agent Tasks Long-Horizon LLM Agents Reinforcement Learning LLM Agent Trajectory Synthesis

Feb 16, 2026

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper's proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt to surpass strong human baselines on the paper's metrics. In a controlled evaluation of an agent powered by GPT-5, we observe a sharp capability--reliability gap. The agent improves over the provided baselines from the repository in just 1 of 15 evaluations (6.7%) by 11.5%, and completes only 26.5% of sub-tasks on average. We identify recurring long-horizon failure modes, including impatience, poor time and resource management, overconfidence in weak hypotheses, difficulty coordinating parallel experiments, and hard limits from context length. Yet in a single run, the agent surpasses the solution of an ICML 2025 Spotlight task, indicating that frontier agents can occasionally reach state-of-the-art performance, but do so unreliably. We additionally evaluate proprietary agent scaffolds including Claude Code (Opus-4.5) and Codex (GPT-5.2) which display a similar gap. ResearchGym provides infrastructure for systematic evaluation and analysis of autonomous agents on closed-loop research.

Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan

TCS Research · Yale University

AI Agent Benchmarks Autonomous Research Agents Automated Agent Evaluation Long-Horizon LLM Agents AI Agent Reliability

Feb 14, 2026

PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning

Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool planning is challenging, because the exploration space suffers from a combinatorial explosion. In this scenario, even when a correct tool-use path is found, it is usually considered an immediate reward for current training, which would not provide any reusable information for subsequent training. In this paper, we argue that historically successful trajectories contain reusable tool-transition patterns, which can be leveraged throughout the whole training process. Inspired by ant colony optimization where historically successful paths can be reflected by the pheromone, we propose Pheromone-Guided Policy Optimization (PhGPO), which learns a trajectory-based transition pattern (i.e., pheromone) from historical trajectories and then uses the learned pheromone to guide policy optimization. This learned pheromone provides explicit and reusable guidance that steers policy optimization toward historically successful tool transitions, thereby improving long-horizon tool planning. Comprehensive experimental results demonstrate the effectiveness of our proposed PhGPO.

Yu Li, Guangfeng Cai, Shengtian Yang +5

School of Computer Science and Engineering, Southeast University, Nanjing, China · Huawei Noah’s Ark Lab, China

LLM-Guided RL Tool-Use Planning Long-Horizon LLM Agents RL for Tool Use

Feb 11, 2026

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently emerged as a promising solution for training such agents in multi-turn settings, allowing them to learn long-horizon decision-making strategies. However, existing pipelines face a critical challenge in balancing task performance with user engagement, as passive agents cannot efficiently adapt to users' intentions while overuse of human feedback increases the burden on users, which forms a Pareto Frontier between these two objectives. To push forward this frontier, we propose Behavior Agentic Optimization (BAO), an agentic RL framework that enhances and regularizes inter-turn behaviors to improve information-gathering capabilities and suppress inefficient or redundant interactions with users. We evaluate BAO on multiple tasks from the UserRL benchmark suite and demonstrate that it substantially outperforms proactive agentic RL baselines in terms of both higher task performance and lower user efforts, while achieving comparable or even superior performance to commercial LLM agents, highlighting its effectiveness for training proactive, user-centric LLM agents in complex multi-turn scenarios. Our website: https://proactive-agentic-rl.github.io/.

Yihang Yao, Zhepeng Cen, Haohong Lin +6

Carnegie Mellon University · Salesforce AI Research · Massachusetts Institute of Technology +2

Agentic RL LLM Agents Long-Horizon LLM Agents

Jan 9, 2026

StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.

Ruizhe Zhang, Xinke Jiang, Zhibang Yang +12

School of Computer Science, Peking University, Beijing, China · 2National Engineering Research Center for Software Engineering, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +5

Multi-Agent LLM Systems Multi-Agent Collaboration Long-Horizon LLM Agents Memory-Augmented Language Model Agents

Jan 4, 2026

CaveAgent: Transforming LLMs into Stateful Runtime Operators

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift. We present CaveAgent, a framework that shifts tool use from LLM-as-Text-Generator'' to LLM-as-Runtime-Operator.'' CaveAgent introduces a dual-stream architecture that inverts the conventional paradigm: rather than treating the LLM's text context as the primary workspace with tools as auxiliary, CaveAgent elevates the persistent Python runtime as the central locus of state, with a lightweight semantic stream serving as its orchestrator. Beyond leveraging code generation to resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, CaveAgent introduces Stateful Runtime Management: it injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns, unlike existing code-based approaches that remain text-bound. CaveAgent further provides a runtime-integrated skill management system that extends the Agent Skills open standard, enabling ecosystem interoperability through executable skill injections. This persistence mechanism serves as a high-fidelity external memory that reduces context drift in multi-turn interactions and preserves processed data for downstream applications without information loss. Evaluations show consistent improvement across challenging benchmarks, enabling CaveAgent to handle data scales that cause context overflow in both JSON-based and code-based agents. The accessible runtime state further provides programmatically verifiable feedback, enabling automated evaluation and reward signal generation without human annotation and establishing a structural foundation for future research in Reinforcement Learning with Verifiable Rewards (RLVR).

Maohao Ran, Zhenglin Wan, Cooper Lin +21

HKUST · HKBU · NUS +8

LLM Agent Memory LLM Agents Long-Horizon LLM Agents LLM Context Management

May 17, 2025

LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?

Interactive benchmarks for LLMs usually report a single metric, even though succeeding in them requires models to show several different skills. While those benchmarks are useful for measuring the overall capability of models to perform the downstream task, it is harder to identify which skill was lacking and caused failure solely from the aggregate score. For example, in benchmarks where models are supposed to navigate a simulated world to perform a task, failures can come from perception, an ambiguous instruction, retrieval, missing commonsense about what actions do, unknown dynamics, or planning. \benchmark recasts the procedurally generated BabyAI gridworld as a fully observable, purely textual environment designed to evaluate planning separately from those factors. The nature of the environment and the structure of the prompt control for the other factors cited above. To evaluate the models, we define the PPD suite: Predict asks for the state that follows an action sequence, Plan asks for an action sequence that reaches a goal, and Decompose asks for a subgoal sequence that achieves a mission. Across seven frontier and open models, queried zero-shot, we find simulation far ahead of planning for every model, close to saturated for the strongest. The length of the required solution governs planning failure, and each of the four strongest models has a horizon beyond which single-attempt success collapses. The responses of claude-opus-4-6 and claude-sonnet-4-6, which show their working step by step, reveal that they plan by proposing L-shaped corridors, which is consistent with their successful plans staying near-optimal while success falls. At the subgoal level, decomposition precision likewise falls to zero on long missions, while comprehension of those missions persists.

Idriss Malek, Omar Choukrani, Daniil Orel +5

Tandon School of Engineering New York University · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi, UAE

LLM Planning LLM Agent Evaluation AI Agent Benchmarks Long-Horizon LLM Agents