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.

Jun 4, 2026

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.

Yasmine Omri, Ziyu Gan, Zachary Broveak +6

Stanford University · Independent Researcher · MICAS, KU Leuven +1

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

Jun 4, 2026

Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents

LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing RAG and agent memory systems organize histories by semantic similarity, retrieving content-relevant entries at decision time. We argue that this design mismatches execution-state dependencies: it fragments decision trajectories and mixes valid and erroneous traces, hindering coherent state reconstruction and error isolation. We propose MAGE (Memory as Agent-Guided Exploration), an active execution-state manager that stores interactions in a hierarchical state tree. The agent derives its state from the active root-to-current path, combining subgoal summaries, recent traces, and hints from prior branches. Four coupled operations maintain the tree: Grow records new traces, Compress summarizes completed subgoals, Maintain validates summaries, and Revise restores a target boundary and resumes on a new branch. This design bounds context growth while preserving state integrity and isolating flawed segments from the active path. Experiments on MemoryArena show that MAGE improves the average task success rate by 7.8--20.4 pp over baselines, while reducing token consumption by 55.1%.

Yaoqi Chen, Haibin Lai, Yuru Feng +12

University of Science and Technology of China · Microsoft · University of California, San Diego +1

Agent Memory Long-Horizon LLM Agents Agent Memory Management

Jun 4, 2026

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.

Wenbo Pan, Shujie Liu, Chin-Yew Lin +5

City University of Hong Kong · Microsoft Research Asia

Software Engineering Agents Agent Harness Optimization LLM Agent Self-Improvement Long-Horizon LLM Agents

Jun 4, 2026

AdaMEM: Test-Time Adaptive Memory for Language Agents

A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions. While recent work demonstrates the promise of agentic memory mechanisms, most systems restrict retrieval to episode initiation. Consequently, agents are forced to rely on static guidance that becomes increasingly misaligned as long-horizon tasks unfold. To address this rigidity, we propose the Adaptive Memory Agent (AdaMEM), a novel framework for agent test-time adaptation. Without updating model parameters online, AdaMEM adapts agent behavior via a hybrid memory architecture: it maintains a long-term trajectory memory of raw experiences collected offline while generating dynamic short-term strategy memory on-the-fly to guide decision-making. This mechanism enables the trade-off between token efficiency and adaptability across varying inference-time compute levels. Empirically, AdaMEM significantly outperforms static memory baselines, achieving relative gains of up to 13% on ALFWorld and 11% on WebShop, with consistent leading performance extending to agentic search on HotpotQA. To further enhance this adaptation, we develop STEP-MFT, a Step-wise Memory Fine-Tuning technique that trains the policy to synthesize high-quality strategies from retrieved experiences, yielding additional performance gains. Our work establishes a new scaling dimension for agentic memory, supporting continuous reasoning and self-evolution post-deployment in real-world environments. Our code is available at https://github.com/yunx-z/AdaMEM.

Yunxiang Zhang, Yiheng Li, Ali Payani +1

University of Michigan · 2Cisco Research.

Agent Memory Test-Time Adaptation LLM Agent Memory LLM Agent Training Long-Horizon LLM Agents

Jun 3, 2026

Personal AI Agent for Camera Roll VQA

We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from simple factual questions (e.g., Name of the food I tried yesterday?'') to more open-ended ones (e.g., Recommend some dishes I have never eaten before''). Given the vast nature of the personal camera roll (i.e., multiple years, hundreds to thousands of photos), a successful AI assistant needs to understand a long-horizon, highly personalized visual content stream in order to navigate and locate the correct and/or relevant information. To support this, we collect and manually annotate questions that mimic real-world usage. The final dataset, camroll, contains 50 users, 31,476 images, and 2,500 QA pairs. We further design camroll-agent, a conversational AI agent equipped with hierarchical memory and a minimal set of tools for efficient navigation over large, personalized visual memory. Experimental results show that camroll-agent outperforms numerous baselines and methods for long-context understanding AI agents system. Together, the camroll dataset and camroll-agent highlight the gap in AI agents' long-context reasoning: personalized visual memory requires different approaches from standard long-context textual memory, especially when consistency, visual details, and user-specific context are present.

Thao Nguyen, Krishna Kumar Singh, Donghyun Kim +2

University of Wisconsin-Madison · Adobe Research · Korea University

Visual Question Answering Long-Horizon LLM Agents Memory-Augmented Agents Personal AI Agents

Jun 2, 2026

Multi $^2$ : Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments

A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynamic environments. While recent LLM-based agents exhibit impressive contextual reasoning, their long-horizon decision-making remains fragile, often suffering from objective drift, where goals and plans drift over extended interactions. We introduce Multi

^2

, a hierarchical multi-agent decision-making framework that explicitly decomposes agent behavior into complementary roles. A high-level agent (System 1) focuses on context-aware sub-goal generation using supervised fine-tuning (SFT), while a low-level agent (System 2) executes atomic actions through offline-to-online reinforcement learning (RL) in interactive environments. This separation enables stable long-horizon control, mitigates objective drift, and allows efficient adaptation. Across diverse interactive environments, Multi

^2

consistently outperforms strong agentic baselines, demonstrating improved robustness and coordination in multi-turn interaction. Beyond performance, we introduce and release three hierarchical benchmark datasets, filling a long-standing gap in training and evaluating hierarchical decision-making for LLM-based agents.

Sangeun Park, Minhae Kwon

Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea.

Multi-Agent LLM Systems Hierarchical RL AI Agent Benchmarks Long-Horizon LLM Agents RL for LLM Agents

Jun 2, 2026

MemTrain: Self-Supervised Context Memory Training

Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utilize information accumulated across extended interactions. Existing memory-agent approaches are typically trained end-to-end with reinforcement learning on downstream tasks. However, collecting high-quality annotated problems for memory-intensive scenarios is costly, and the resulting training data often lack sufficient diversity to cover general memory behaviors. In this work, we propose MemTrain, a self-supervised training framework for generally enhancing the context-memory capability of LLM agents for more effective downstream post-training. MemTrain introduces two coupled proxy tasks over unlabeled Wikipedia corpora: (1) an end-to-end masked reconstruction objective, which requires the model to recover masked entities after multiple rounds of memory updates, thereby encouraging memory maintenance from the final outcome perspective; and (2) an intermediate memory recall objective, which requires the model to reconstruct masked historical information using intermediate memory states, encouraging faithful compression and memory completeness throughout the interaction process. The two objectives are jointly optimized using GRPO. Extensive experiments on long-text QA and search-based QA benchmarks demonstrate that MemTrain consistently improves downstream memory-intensive reasoning performance across different models, achieving gains of up to 17.67 points over direct task-specific post-training.

Ziheng Li, Xingrun Xing, Haoqing Wang +2

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Samsung Research, Beijing, China

LLM Agent Memory Persistent Memory for Language Models Long-Horizon LLM Agents Memory-Augmented Language Model Agents Memory Management for LLM Agents

Jun 1, 2026

WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents

Multi-turn user-facing agents must infer user intent from incomplete requests, collect missing information through dialogue and tools, and execute valid actions. A training trajectory records this process as an interleaved sequence of user messages, agent responses, tool calls, etc. Synthesizing sufficiently complex trajectory has become a central route to train agents: existing pipelines often increase difficulty by composing multiple user requests into longer tasks, producing write-intensive trajectories that train sequential execution. We argue that a single write decision can itself be difficult when the agent must gather and compare substantial read-tool evidence before its arguments become identifiable, a challenge that write-intensive data alone cannot address. Guided by this insight, we propose WRIT (\uline{W}rite-\uline{R}ead \uline{I}ntensive \uline{T}rajectory Synthesis), a pipeline for synthesizing multi-turn agent training trajectories along two complexity axes: the number of write decisions in a task and the evidence burden of each individual decision. WRIT first generates write-intensive and read-heavy tasks. It then diversifies user behavior instructions to reflect realistic conversational variation, and finally simulates agent-user interactions in an executable environment to produce complete training trajectories. The resulting data trains agents not only for longer task execution, but also for robust, evidence-grounded decision making under high information load. With only 2K synthesized trajectories, a 4B model trained on WRIT outperforms GPT-5.1 no-think on

τ^2

-bench and substantially reduces inference-time token usage, showing that compact SFT data can convert part of expensive test-time reasoning into efficient agent behavior.

Hengrui Gu, Xiaotian Han, Kaixiong Zhou

North Carolina State University · Case Western Reserve University

Tool-Augmented Language Model Agents Tool-Using Agents LLM Agent Trajectory Synthesis LLM Agent Training Synthetic Data Generation for Language Models Long-Horizon LLM Agents

Jun 1, 2026

CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents

Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, existing textual world models are typically fixed after training, preventing them from adapting to the on-policy state-action distributions induced by an evolving agent. Meanwhile, agent-improvement methods often rely on external rewards or verifiers, limiting their applicability in realistic interactive environments. In this paper, we propose COMAP, a novel framework that co-evolves textual world models and agent policies through closed-loop interaction. At each decision step, the world model predicts future state feedback for candidate actions, and the agent performs future-aware reflection by estimating the reliability of this feedback and refining its action accordingly. The resulting on-policy trajectories are then used to update the world model via self-distillation, allowing it to better match the agent's evolving interaction distribution. Across embodied task planning, Web navigation, and tool-use benchmarks, COMAP consistently outperforms competitive baselines, e.g., +16.75% relative improvement with Qwen3-4B. Further analyses show that the co-evolutionary loop improves the world model's prediction accuracy over time and leads to more effective long-horizon decision-making. Our code is available at: https://github.com/loyiv/CoMAP.

Youwei Liu, Jian Wang, Hanlin Wang +1

Central South University · College of Computer Science, Sichuan University · Department of Computing, The Hong Kong Polytechnic University

LLM World Models LLM Agent Training Long-Horizon LLM Agents Embodied World Models Self-Evolving Agents

Jun 1, 2026

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without external skill generators or inference-time skill banks. SIRI first warms up the policy with GiGPO to acquire basic interaction ability and collect successful skill-free trajectories. It then performs self-skill mining, where the current policy summarizes compact skills from its own successful plain rollouts and validates them through paired skill-augmented and skill-free rollouts. Finally, SIRI distills only beneficial skill-guided action tokens into the plain policy using trajectory-level utility and action-level advantage. At inference, the agent runs with the original prompt only. On ALFWorld and WebShop with Qwen2.5-7B-Instruct, SIRI improves GiGPO from 0.908 to 0.930 on ALFWorld and from 0.728 to 0.813 on WebShop, outperforming prompt-based, RL-based, and memory-augmented baselines. Further analysis shows that our self-mining strategy can achieve performance comparable to distillation with closed-source large model. Our code is available at https://github.com/kirito618/SIRI.

Zhongyu He, Yuanfan Li, Fei Huang +9

Xiamen University · Meituan · Macao Polytechnic University

LLM Agent Skill Learning Long-Horizon LLM Agents RL for LLM Agents

May 31, 2026

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually update skills from full trajectories or session-level feedback, which makes failure attribution coarse and often produces unstable or overly broad revisions. We propose SkillAdaptor, a training-free step-level skill adaptation framework with explicit failure attribution, and it can plug into OpenClaw-class agent harnesses. Given a failed trajectory, SkillAdaptor identifies a first actionable fault step, links responsibility to candidate skills, and applies targeted updates under explicit acceptance checks while keeping the backbone frozen. We evaluate on WebShop, PinchBench, and Claw-Eval with Kimi-K2.5, GLM-5, and GPT-5.2. SkillAdaptor improves over no-skill and skill-adaptation baselines on all three suites, with the largest single-metric improvements of +1.5 points on PinchBench Avg Score%, +1.8 on Claw-Eval Avg Score, and +1.7 on WebShop success rate. These results indicate that step-level attribution supports more stable and auditable training-free skill maintenance\footnote{The code will be released at https://github.com/zjunlp/SkillAdaptor.}.

Zhuoyun Yu, Xin Xie, Wuguannan Yao +4

♠Zhejiang University · ♣Ant Digital Technologies, Ant Group · ♢Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph +1

LLM Agent Skill Learning Failure Attribution for LLM Agents Long-Horizon LLM Agents

May 30, 2026

CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems

LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the lightweight models that fit on edge servers often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection. Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes, while purely local execution confines each agent to its own isolated experience. We propose CoMIC, a parameter-update-free cloud-edge framework for Collaborative Memory and Insights Circulation. Following the paradigm of ``Act at the Edge, Reflect in the Cloud'', edge agents execute locally with subgoal-oriented hierarchical memory and selective re-expansion of relevant histories, while a cloud-side LLM critic asynchronously evaluates the trajectories uploaded through a Web gateway, admits reusable experience, and circulates cross-agent guidance indexed by semantic subgoal identifiers back to all edge agents. On five long-horizon benchmarks, CoMIC enables weak edge agents to achieve non-zero success on tasks where a standard memory-based agent fails entirely, and improves their task progress over both the standard agent and purely local execution while reducing context consumption relative to the standard agent, all without updating model parameters. When stronger heterogeneous agents join the edge, the weak agents further improve in success, progress, and grounding with lower context consumption.

Yannan Wang, Longli Yang, Zhen Liu +2

Beijing Jiaotong University · Visiting PhD student at WMG, University of Warwick. · The Alan Turing Institute +2

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

May 30, 2026

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment for sustained exploration beyond easy high-frequency entities. We propose SPADER, a reinforcement learning framework for long-horizon tool use in Multi-Answer QA. SPADER includes Step-wise Peer Advantage (SPA), a critic-free step-level credit assignment mechanism that aligns parallel trajectories by decision step and estimates advantages from peer returns. It also includes a diversity-aware exploration reward that promotes long-tail entity discovery by upweighting rare findings and downweighting redundant ones. Experiments on QAMPARI, Mintaka, WebQSP, and QUEST show that SPADER generally improves recall and overall F1 over prompting-based agents, outcome-supervised RL methods, and recent step-level supervision approaches. Our code and model weights are available at https://github.com/KhanCold/spader.

Qiming Shi, Zhaolu Kang, Yunfan Zhou +2

State Key Lab of CAD&CG, Zhejiang University · School of Software and Microelectronics, Peking University · School of Software Technology, Zhejiang University

Credit Assignment in RL Step-Level Credit Assignment in RL Question Answering Long-Horizon LLM Agents RL for Tool Use

May 29, 2026

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries are typically treated as model-agnostic, reusing the same skill formulations across backbones with substantially different capacities and behaviors. However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another. Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights. MASA operates in two stages: (1) a hierarchical skill evolution pipeline that iteratively rewrites general and task-specific skills using hill climbing and UCB-driven tree search, guided by environment feedback and model capability profiles; and (2) a lightweight model-conditioned skill rewriter trained on evolution trajectories to reproduce the adaptation in a single forward pass. Experiments across three interactive environments and four backbones show that MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline. The learned rewriter further generalizes to unseen tasks and environments without additional search, consistently outperforming a much larger teacher LLM at a fraction of the inference cost.

Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3

East China Normal University, Shanghai, China

LLM Agent Skill Learning LLM Agent Skill Retrieval LLM Agents Long-Horizon LLM Agents

May 28, 2026

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement learning, failing to localize where intermediate memory quality degrades. As interactions unfold, ambiguous recursive summaries progressively discard task-relevant information and introduce semantic noise. This exacerbates belief deviation, obscuring the agent's estimate of the latent task state and ultimately derailing long-horizon reasoning. We therefore argue that memory optimization should focus not merely on trajectory-level success, but on the clarity of the belief induced by intermediate summaries. To this end, we introduce Belief Entropy, a self-supervised proxy that probes how uncertain the model remains about the latent task state given its current memory. Based on this proxy, we propose Metacognitive Memory Policy Optimization (MMPO). Instead of relying only on sparse outcome-based signals, MMPO provides fine-grained, memory-specific supervision via explicitly penalizing summaries that induce high epistemic uncertainty. Experiments show that MMPO consistently outperforms existing methods on diverse long-horizon tasks, maintaining 97.1% performance even when scaled to 1.75M-token contexts.

Ziyan Liu, Zhezheng Hao, Yeqiu Chen +7

University of Science and Technology of China · Zhejiang University · Tencent

Long-Horizon LLM Agents Memory-Augmented Language Model Agents

May 28, 2026

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents

Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external repositories, which limits domain diversity, environment controllability, and the targeting of specific capability deficits. We introduce LiteCoder-Terminal-Gen, a zero-dependency synthesis pipeline that autonomously generates executable and verifiable terminal training environments directly from domain specifications. Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization. Supervised fine-tuning of Qwen-family models on our SFT dataset yields agents that significantly outperform their base counterparts. Notably, our 32B variant achieves 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro, respectively. Furthermore, applying Direct Multi-turn Preference Optimization (DMPO) on our RL environments yields additional performance gains. These results systematically demonstrate that fully synthetic, executable environments offer a scalable and verifiable supervision signal for mastering complex, real-world command-line workflows.

Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5

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

RL for Language Models Terminal Agents LLM Agent Training Synthetic Data Generation for Language Models Long-Horizon LLM Agents

May 27, 2026

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents

A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep what a user volunteers but rarely ask for what stays unspoken, leaving a proactivity gap in long-lived LLM agents: an agent cannot act on a preference it never obtained. As users delegate more of their affairs to agents, the impact of this gap grows. We isolate one concrete, controllable slice of this gap as Ask-to-Remember (ATR): the agent decides whether to ask now for a reusable user preference that the current task does not need but a later session with the same user will. ATR is hard even to evaluate: the right question is underdetermined and its payoff deferred to tasks that may never arise. ATRBench, to the best of our knowledge the first ATR benchmark, makes it measurable by fixing each user's preferences as hidden ground truth, so success demands asking, not recall. Across eight frontier LLM agents, defaults fall at least 62 points below an oracle handed the relevant preference, and prompting closes little of it. Diagnostics identify acquisition as the bottleneck. ATRBench surfaces this proactivity gap in current agents and offers a diagnostic testbed for closing it.

Bin Wu, Guanyun Zou, Bingbing Wang +2

Beijing University of Posts and Telecommunications · Nanjing University of Aeronautics and Astronautics · Harbin Institute of Technology (Shenzhen) +1

Proactive Assistance LLM Agent Memory LLM Agent Evaluation Agent Benchmarks Long-Horizon LLM Agents Preference Elicitation+1

May 27, 2026

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning, tool use, and iterative state updates, remains unclear. We study this question through a systematic layer-wise analysis of complete user-agent trajectories spanning three domains: Deep Research, Code Generation, and Tabular Processing. Using residual stream probes, causal layer-skipping interventions, and effective-depth measurements, we show that agentic reasoning exhibits a distinct depth profile from static tasks. As trajectories unfold, models progressively recruit more and deeper layers, with stronger long-range inter-layer dependencies emerging in later turns. At the same time, residual updates become increasingly correction-dominant, indicating a shift from stable feature accumulation toward repeated recalibration. Effective-depth analysis further reveals a substantial construction-refinement gap: semantic direction often forms relatively early, while deep layers remain necessary for stabilizing final outputs. Across model families, this gap is pronounced in Qwen and Minimax, whereas GLM shows a more domain-dependent depth allocation pattern. These results provide mechanistic evidence that autonomous LLM agents allocate depth adaptively as reasoning complexity grows.

Zhenyu Cui, Xiangzhong Luo

LLM Interpretability Mechanistic Interpretability Long-Horizon LLM Agents Adaptive Computation

May 26, 2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

MiniMax, :, Aili Chen +204

Mixture-of-Experts Language Models Agentic RL AI Coding Agents LLM Agent Training Long-Horizon LLM Agents AI Agent Architecture

May 25, 2026

Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions

Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, personalized assistance requires more than following generic instruction or recognizing object categories. In real-world scenarios, the intended target is often specified only implicitly through prior interactions, requiring agents to leverage personalized context accumulated over time. In this work, we propose POLAR, a multiomodal memory-augmented framework for personalized embodied agents over long-term user interactions. POLAR organizes prior interactions into a multimodal knowledge graph that captures semantic memory for personalized context and visual concepts, and episodic memory for embodied experiences such as agent trajectories. To execute embodied tasks, POLAR retrieves relevant memories to interpret the current request and guide task execution. We evaluate POLAR across multiple MLLM backbones and diverse evaluation scenarios to study the role of memory in long-term personalization. Results show that the proposed memory mechanism consistently improves performance by enabling more effective use of information accumulated over prior interactions. The gains are especially pronounced when the agents are required to reason across multiple interactions, perform multi-hop inference, or tracking updates in user-specific context over time.

Jeongeun Lee, Chanyoung Park, Dongha Lee

Yonsei University · KAIST

Multimodal Memory Embodied AI Long-Horizon LLM Agents Memory-Augmented Language Model Agents Long-Term Memory for Embodied Agents

May 25, 2026

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks similarly provide only partial user state and therefore fail to capture performance in such a broad, always-on setting. To address this gap, we introduce Claw-Anything, a benchmark that expands agent context along three dimensions: long-horizon activity histories, interdependent backend services, and integrated GUI and CLI interaction across multiple devices. To instantiate this setting, we simulate months of user activity through multi-round event injection, producing complex world states and realistic noise, including irrelevant events and conflicting signals. Agents must reason over rich contextual environments while remaining robust to such noise. This expanded scope also enables the evaluation of proactive assistance, requiring agents to anticipate user needs and deliver timely recommendations. Experiments show that GPT-5.5 achieves only 34.5% pass@1, substantially below prior benchmarks, underscoring a gap between current agent capabilities and the demands of always-on personal assistance. Alongside the benchmark, we release an automated data-generation pipeline that yields 2,000 training environments and improves the base model by 23.7%, demonstrating its utility of scalable data infrastructure.

Yusong Lin, Xinyuan Liang, Haiyang Wang +8

Beijing Institute of Technology · Huawei Technologies Co., Ltd · Peking University +1

Computer-Use Agent Benchmarks AI Agent Benchmarks Proactive Assistance Long-Horizon LLM Agents Personal AI Agents

May 25, 2026

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory budget on transient interactions while failing to preserve critical context for long horizon tasks. To address this gap, we investigate an underexplored question: can LLM based memory systems learn personalized memory policies? We introduce PerMemBench, the first benchmark for evaluating personalized memory systems, featuring multi year, multi domain interaction histories across diverse user personas. We further present the first empirical study of memory personalization, proposing session level storage gating, a lightweight framework that selectively bypasses memory operations for transient sessions. Our study confirms that personalization yields substantial retention gains under perfect gating, yet reveals that accurate gating remains an open and critical challenge.

Yeonjun In, Wonjoong Kim, Sangwu Park +2

KAIST

Memorization in Language Models Persistent Memory for Language Models Memory Agent Benchmarks Long-Horizon LLM Agents Agent Memory Management

May 23, 2026

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

Yuxin Zhang, Mengxue Hu, Zheng Lin +8

1Fudan University · 2Alibaba Group · 3The University of Hong Kong +4

LLM Agent Training LLM Routing Long-Horizon LLM Agents RL for LLM Agents

May 23, 2026

DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback

Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each rollout is costly, and a limited interaction budget may yield few examples of effective behavior. Sparse, delayed feedback also makes it difficult for a coding agent to diagnose failures and determine which modifications will improve performance. We present DemoEvolve, which uses human demonstrations to guide harness evolution under limited interaction budgets. The coding agent examines demonstrations alongside its own rollout history, extracts strategies and the conditions under which they apply, and turns them into reusable harness components. We compare demonstration guidance with self-rollout evolution and augmentation with retrieved textual knowledge under the same evolution procedure and agent interaction budget. On held-out seeds, DemoEvolve improves mean capped final-round progress from 16.83 to 20.00 in Balatro and mean floor reached from 18.17 to 28.83 in Slay the Spire 2, compared with the respective base harnesses. These results suggest that demonstrations can help harness evolution make better use of limited interaction experience by providing concrete guidance for diagnosis and modification.

Lirong Che, Yuzhe yang, Peiwen lin +4

Tsinghua University · AgiBot

Agent Harness Optimization LLM Agent Self-Improvement Learning from Demonstration Long-Horizon LLM Agents

May 23, 2026

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether multiple peer agents, all targeting the same task, can become an additional source of capability without relying on explicit role specialization or workflow orchestration. We study this question and propose AgentFugue, a collective reasoning framework built around a shared reasoning hub. As peer agents explore the same task in parallel, the hub records concise notes on what each agent has established, attempted, or ruled out, and enables each agent to selectively access what other agents have discovered in a form useful for its current search. This design turns otherwise isolated trajectories into a connected ecology of reusable intermediate reasoning without requiring centralized planning. We instantiate the hub as a plug-in communication layer, trained with supervised fine-tuning and end-to-end reinforcement learning. Across the challenging long-horizon settings we study, AgentFugue improves over strong baselines. Our results suggest that collective reasoning can turn scaling out peer agent systems into a distinct source of capability gains, rather than merely a way of spending more compute.

Yuyang Hu, Hongjin Qian, Shuting Wang +5

GSAI, Renmin University of China · Beijing Academy of Artificial Intelligence

Multi-Agent Reasoning Long-Horizon LLM Agents Multi-Agent Communication Memory-Augmented Language Model Agents

May 22, 2026

An Interactive Paradigm for Deep Research

Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval, reasoning, and generation. Yet most frameworks rely on rigid workflows with one-shot scoping and long autonomous runs, offering little room for course correction if user intent shifts mid-process. We present SteER, a framework for Steerable deEp Research that introduces interpretable, mid-process control into long-horizon research workflows. At each decision point, SteER uses a cost-benefit formulation to determine whether to pause for user input or to proceed autonomously. It combines diversity-aware planning with utility signals that reward alignment, novelty, and coverage, and maintains a live persona model that evolves throughout the session. SteER outperforms state-of-the-art open-source and proprietary baselines by up to 22.80% on alignment, leads on quality metrics such as breadth and balance, and is preferred by human readers in 85%+ of pairwise alignment judgments. We also introduce a persona-query benchmark and data-generation pipeline. To our knowledge, this is the first work to advance deep research with an interactive, interpretable control paradigm, paving the way for controllable, user-aligned agents in long-form tasks.

Lin Ai, Victor S. Bursztyn, Xiang Chen +2

Department of Computer Science, Columbia University, New York, NY, USA · Adobe Research, San Jose, CA, USA

Deep Research Agents Human-in-the-Loop AI Long-Horizon LLM Agents

May 22, 2026

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.

Jian Xie, Tianhe Lin, Zilu Wang +16

The Ohio State University · Amazon AGI SF Lab

Deep Research Agents LLM Agent Training Synthetic Data Generation for Language Models Long-Horizon LLM Agents

May 22, 2026

Parallel Context Compaction for Long-Horizon LLM Agent Serving

Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conversation bounded, but summarization is inherently lossy and the blocking call stalls agent inference for tens of seconds. Moreover, the operator has no fine-grained control over summary volume since prompt instructions are largely ignored, and as context grows, both the amount of output tokens the model produces and the information it retains fluctuate substantially from run to run, making the agent's retained knowledge unpredictable across runs. We introduce parallel compaction for long-horizon agentic flows and characterize it against the sequential synchronous baseline across four backbones spanning 8B to 120B parameters, mixing dense and MoE architectures with reasoning and non-reasoning models, on the HotpotQA multi-hop QA and LoCoMo long-context dialogue benchmarks. Parallel compaction gives the operator fine-grained, predictable control over summary volume and enables more targeted prompt engineering per block. At matched compaction decode volume, it reduces end-to-end wall time and improves compaction throughput over the sequential baseline.

Musa Cim, Burak Topcu, Chita Das +1

The Pennsylvania State University

LLM Inference Efficiency LLM Agent Workflow Optimization Long-Horizon LLM Agents LLM Context Management Context Compaction for LLM Agents

May 21, 2026

Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play

Static benchmarks capture only part of how large language models behave in practice. Real systems place models inside repeated loops with time limits, formatting constraints, and failure modes. We study this setting in a timed multi-phase Risk environment with explicit victory targets and repeated planning and execution cycles. In a replicated 32-game cross-provider championship under frozen rules, gemini-3.1-pro-preview won 20 of 32 games against gpt-5.1, claude-opus-4-7, and kimi-k2.6, and the pooled winner distribution differs strongly from an equal-strength null (p approx 1.5 x 10^-5). We then separate planning from execution by standardizing execution on a cheaper Gemini Flash scaffold. Under this design, a pooled 32-game planner bakeoff is consistent with near-equality (p approx 0.821), which indicates that much of the earlier provider spread came from end-to-end system behavior rather than planning alone. To study mechanism, we analyze saved planning and execution traces from the provider championship. Gemini refers to the terminal objective far more often than the other models and increases that focus as victory approaches. Gemini also converts more turns into deep conquest chains, even though it is not the cleanest runtime. These results show that live-agent performance depends on objective tracking, execution conversion, cost, and runtime reliability, and they support evaluating LLMs as components in bounded workflows rather than as isolated benchmark respondents.

H. C. Ekne

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

May 21, 2026

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents

Large language model (LLM)-based agents solve complex tasks by leveraging multi-step reasoning with iterative tool calls and environment interactions, which incur idle time while waiting for observations. Despite the prevalence of idle time in most agentic scenarios, existing works treat it as an unavoidable overhead or propose restricted solutions that overlook varying computational budgets across different tool calls and future observation uncertainty, thereby leading to suboptimal utilization of idle time. In this paper, we introduce IdleSpec, a scalable and generic inference approach that leverages idle-time computation to improve agent performance while minimizing latency overhead. Specifically, IdleSpec iteratively generates plan candidates during idle periods and, once observations become available, aggregates them to guide the next reasoning step. For effective plan generation under observation uncertainty, IdleSpec samples between complementary drafting strategies (i.e., progressive and recovery) from a learned distribution that is updated via posterior feedback. Our experiments demonstrate that IdleSpec significantly improves agent performance in various agentic scenarios by effectively utilizing idle time. In particular, on the GAIA and FRAMES, IdleSpec achieves 55.6% average accuracy with Gemini-2.5-Flash, surpassing the vanilla baseline without idle-time usage by 5.1%. Furthermore, for MLE-Bench, which involves substantial delay from code executions, IdleSpec achieves performance gains of up to 9.1% on the Any Medal rate, highlighting its generalizability to long-horizon tasks.

Daewon Choi, Kyunghyun Park, Woomin Song +4

1KAIST · 3Together AI · 2Amazon AGI

LLM Inference Efficiency Long-Horizon LLM Agents LLM Agent Planning