LLM Agent Planning

LLM: Large Language Model

Follow this topic Ask about this topic

LLM agent planning studies how language models can turn instructions into sequences of actions that achieve goals in tools, software, websites, and physical or simulated environments. Common approaches include ReAct-style plan-and-act loops, hierarchical subgoals and skill graphs, symbolic planners such as PDDL, search methods such as tree search, and world models that predict action outcomes; reinforcement learning and trajectory feedback are also used to improve these systems. Evaluations span web and GUI navigation, coding, household tasks, games, and tool-use benchmarks, increasingly testing long horizons, changing conditions, tool failures, and resource costs. A central challenge is that a plausible plan does not guarantee faithful or safe execution: agents must track state, ground tool arguments, verify results, and recover when assumptions or plans fail.

Latest papers

226 papers38 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Apr 13, 2026

CocoaBench: Evaluating Unified Digital Agents in the Wild

LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most evaluations still test these capabilities in isolation, which leaves a gap for more diverse use cases that require agents to combine different capabilities. We introduce CocoaBench, a benchmark for unified digital agents built from human-designed, long-horizon tasks that require flexible composition of vision, search, and coding. Tasks are specified only by an instruction and an automatic evaluation function over the final output, enabling reliable and scalable evaluation across diverse agent infrastructures. We also present CocoaAgent, a lightweight shared scaffold for controlled comparison across model backbones. Experiments show that current agents remain far from reliable on CocoaBench, with the best evaluated system achieving only 45.1% success rate. Our analysis further points to substantial room for improvement in reasoning and planning, tool use and execution, and visual grounding.

CocoaBench Team, Shibo Hao, Zhining Zhang +29

AI Agent Benchmarks Computer-Use Agent Evaluation Tool-Using Agents Long-Horizon Agent Evaluation Automated Agent Evaluation LLM Agent Planning

Apr 13, 2026

From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience

Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.

Jia Luo

Huazhong University and Science and Technology Wuhan, China

LLM Agent Planning Supply Chain Management RL for LLM Agents Latent World Models

Apr 13, 2026

HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation

Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this, we propose Hybrid Toolset Agentization & Adaptation (HTAA), a hierarchical framework for scalable tool-use planning. We propose a novel toolset agentization paradigm, which encapsulates frequently co-used tools into specialized agent tools, thereby reducing the planner's action space and mitigating redundancy. To ensure effective coordination, we design Asymmetric Planner Adaptation, a trajectory-based training paradigm that aligns the high-level planner with agent tools via backward reconstruction and forward refinement. To validate the performance of HTAA, we conduct experiments on a real-world internal dataset, InfoVerify, based on the POI validation workflow of China's largest online large-scale ride-hailing platform, featuring long-horizon executable tool trajectories. Experiments on InfoVerify and widely-used benchmarks show that HTAA consistently achieves higher task success rates, requires short tool calling trajectories, and significantly reduces context overhead compared to strong baselines. Furthermore, in a production deployment, HTAA substantially reduces manual validation effort and operational cost, demonstrating its practical efficacy.

Chengrui Huang, Junshuo Zhang, Zhiyuan Ma +7

University of Electronic Science and Technology of China · 2DiDi Global Inc.

Tool-Use Planning LLM Tool Use LLM Agent Planning LLM Agent Training Long-Horizon Agent Tasks

Apr 11, 2026

Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision

Current evaluations of autonomous coding agents assume an unrealistic, infinite-resource environment. However, real-world software engineering is a resource-bound competition. As we scale toward large agent swarms, ignoring compute and time costs risks catastrophic budget exhaustion. To shift the focus from isolated accuracy to cost-aware problem-solving, we introduce USACOArena, an interactive ACM-ICPC-style arena driven by a strict "credit" economy. Every generated token, local test, and elapsed second depletes a fixed budget, forcing agents to make strategic trade-offs. Our comprehensive profiling reveals that frontier single agents and swarms currently fail to optimally balance accuracy with these constraints, exhibiting divergent, path-dependent behaviors. Ultimately, USACOArena provides an essential dynamic training ground for developing highly efficient, resource-aware agent architectures.

Lingfeng Zhou, Junhao Shi, Jin Gao +1

Shanghai Jiao Tong University · Shanghai Innovation Institute

Software Engineering Agents AI Agent Benchmarks Multi-Agent Coding LLM Agent Planning

Apr 8, 2026

How Much Heavy Lifting Can an Agent Harness Do?: Measuring the LLM's Residual Role in a Planning Agent

Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as much as six times. That raises a question asked less often than it should be: how much of an agent's competence does the harness itself already carry, and how much genuinely still needs the LLM? We externalize a planning harness for noisy Collaborative Battleship into four progressively richer layers -- posterior belief tracking, declarative planning, symbolic reflec tion, and an LLM-backed revision gate -- under a common runtime, taking win rate as the primary metric and F1 as secondary, and pre-specifying heavy lifting as the single largest positive marginal to the primary metric. Across 54 games, declarative pla nning carries the heavy lifting (

+24.1

pp win rate over a belief-only harness, zero LLM calls); symbolic reflection is mechanistically real but calibration-sensitive, with signed board-level effects up to

\pm0.140

F1 that cancel on aggregate; and LLM-backed revision ac tivates on only

4.3\%

of turns with a bounded, non-monotonic effect. The contribution is methodological: once harness layers are made externally measurable, the LLM's role can be quantified as residual rather than assumed central.

Sungwoo Jung, Seonil Son

Independent Researcher · RLWRLD.AI Seoul, South Korea

Automated Agent Evaluation LLM Agent Harnesses LLM Agent Planning

Apr 7, 2026

AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments

Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To address these issues, we propose AgentCE-Bench built around a unified grid-based planning task, where agents must fill hidden slots in a partially completed schedule subject to both local slot constraints and global constraints. Our benchmark offers fine-grained control through two orthogonal axes: Scalable Horizons, controlled by the number of hidden slots

H

, and Controllable Difficulty, governed by a decoy budget

B

that determines the number of globally misleading decoy candidates. Crucially, all tool calls are resolved via static JSON files under a Lightweight Environment design, eliminating setup overhead and enabling fast, reproducible evaluation suitable for training-time validation. We first validate that

H

and

B

provide reliable control over task horizon and difficulty, and that AgentCE-Bench exhibits strong domain consistency and model discriminability. We then conduct comprehensive experiments across 13 models of diverse sizes and families over 6 domains, revealing significant cross-model performance variation and confirming that AgentCE-Bench provides interpretable and controllable evaluation of agent reasoning.

Wang Yang, Chaoda Song, Xinpeng Li +7

Case Western Reserve University · NII LLMC (Japan) · University of Zurich

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

Apr 7, 2026

SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation

LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool descriptions. As a result, semantic-only methods can produce negative Kendall-

τ

in structured workflow domains. We introduce SkillGraph, a directed weighted execution-transition graph mined from 49,831 successful LLM agent trajectories, which encodes workflow-precedence regularities as a reusable graph foundation prior. Building on this graph foundation prior, we propose a two-stage decoupled framework: GS-Hybrid retrieval for candidate selection and a learned pairwise reranker for ordering. On ToolBench (9,965 test instances; ~16,000 tools), the method reaches Set-F1 = 0.271 and Kendall-

τ

= 0.096; on API-Bank, Kendall-

τ

improves from -0.433 to +0.613. Under identical Stage-1 inputs, the learned reranker also outperforms LLaMA-3.1-8B Stage-2 rerankers.

Hao Liu, Dongyu Li

Tool-Using Language Agents Tool Selection for Language Model Agents LLM Agent Planning Tool Discovery for LLM Agents Graph-Based Retrieval LLM Reranking

Apr 1, 2026

$\texttt{YC-Bench}$ : Benchmarking AI Agents for Long-Term Planning and Consistent Execution

As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound. We introduce

\texttt{YC-Bench}

, a benchmark that evaluates these capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns. The agent must manage employees, select task contracts, and maintain profitability in a partially observable environment where adversarial clients and growing payroll create compounding consequences for poor decisions. We evaluate 12 models, both proprietary and open source, across 3 seeds each. Only three models consistently surpass the starting capital of $200K, with Claude Opus 4.6 achieving the highest average final funds at $1.27 M, followed by GLM-5 at $1.21 M at 11

\times

lower inference cost. Scratchpad usage, the sole mechanism for persisting information across context truncation, is the strongest predictor of success, and adversarial client detection is the primary failure mode, accounting for

47\%

of bankruptcies. Our analysis reveals that frontier models still fail through distinct failure modes such as over-parallelization, demonstrating the capability gaps for long-horizon performance.

\texttt{YC-Bench}

is open-source, reproducible, and configurable.

Muyu He, Adit Jain, Anand Kumar +4

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

Mar 27, 2026

ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent in human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process. This allows an orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing. The foundation of this framework is a Dual-Memory architecture: a mutable working memory that maintains the evolving patient state for context-aware reasoning, and a static experience memory that retrieves clinical guidelines and historical cases via an active feedback loop. Extensive experiments demonstrate that ClinicalAgents achieves the best performance among evaluated baselines, significantly enhancing both diagnostic accuracy and explainability compared to strong single-agent and multi-agent baselines. Our code is released at https://github.com/ZhuohanGe/ClinicalAgents-Code.

Zhuohan Ge, Haoyang Li, Yubo Wang +3

The Hong Kong Polytechnic University, Hong Kong SAR, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China

Clinical Decision-Making Multi-Agent LLM Systems Medical Diagnosis Clinical Reasoning Memory-Augmented Language Model Agents LLM Agent Planning

Mar 25, 2026

Composer 2 Technical Report

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.

Cursor Research, :, Aaron Chan +53

Code Language Models Software Engineering Agents LLM Agent Planning RL for Code Generation Software Engineering Benchmarks

Mar 25, 2026

Language-Grounded Multi-Agent Planning for Personalized and Fair Participatory Urban Sensing

Participatory urban sensing leverages human mobility for large-scale urban data collection, yet existing methods typically rely on centralized optimization and assume homogeneous participants, resulting in rigid assignments that overlook personal preferences and heterogeneous urban contexts. We propose MAPUS, an LLM-based multi-agent framework for personalized and fair participatory urban sensing. In our framework, participants are modeled as autonomous agents with individual profiles and schedules, while a coordinator agent performs fairness-aware selection and refines sensing routes through language-based negotiation. Experiments on real-world datasets show that MAPUS achieves competitive sensing coverage while substantially improving participant satisfaction and fairness, promoting more human-centric and sustainable urban sensing systems.

Xusen Guo, Mingxing Peng, Hongliang Lu +3

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

Multi-Agent Planning LLM Agent Planning

Mar 25, 2026

DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction

While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability in long-horizon domains. To bridge the gap between unstructured environments and rigorous plan synthesis, we propose DUPLEX, an agentic dual-system neuro-symbolic architecture that strictly confines the LLM to schema-guided information extraction rather than end-to-end planning or code generation. In our framework, a feed-forward Fast System utilizes a lightweight LLM to extract entities, relations etc. from natural language, deterministically mapping them into a Planning Domain Definition Language (PDDL) problem file for a classical symbolic planner. To resolve complex or underspecified scenarios, a Slow System is activated exclusively upon planning failure, leveraging solver diagnostics to drive a high-capacity LLM in iterative reflection and repair. Extensive evaluations across 12 classical and household planning domains demonstrate that DUPLEX significantly outperforms existing end-to-end and hybrid LLM baselines in both success rate and reliability. These results confirm that The key is not to make the LLM plan better, but to restrict the LLM to the part it is good at - structured semantic grounding - and leave logical plan synthesis to a symbolic planner.

Keru Hua, Ding Wang, Yaoying Gu +1

Midea Corporate Research Center, Midea Group, Foshan, China · Robot Science and Engineering Department, Northeastern University, Shenyang, China

Robot Task Planning LLM Agent Planning Neuro-Symbolic Planning Neuro-Symbolic Reasoning Symbolic Planning

Mar 24, 2026

Environment Maps: Structured Environmental Representations for Long-Horizon Agents

Although large language models (LLMs) have advanced rapidly, robust automation of complex software workflows remains an open problem. In long-horizon settings, agents frequently suffer from cascading errors and environmental stochasticity; a single misstep in a dynamic interface can lead to task failure, resulting in hallucinations or trial-and-error. This paper introduces

\textit{Environment Maps}

: a persistent, agent-agnostic representation that mitigates these failures by consolidating heterogeneous evidence, such as screen recordings and execution traces, into a structured graph. The representation consists of four core components: (1) Contexts (abstracted locations), (2) Actions (parameterized affordances), (3) Workflows (observed trajectories), and (4) Tacit Knowledge (domain definitions and reusable procedures). We evaluate this framework on the WebArena benchmark across five domains. Agents equipped with environment maps achieve a 28.2% success rate, nearly doubling the performance of baselines limited to session-bound context (14.2%) and outperforming agents that have access to the raw trajectory data used to generate the environment maps (23.3%). By providing a structured interface between the model and the environment, Environment Maps establish a persistent foundation for long-horizon planning that is human-interpretable, editable, and incrementally refinable.

Yenchia Feng, Chirag Sharma, Karime Maamari

Distyl AI

Long-Horizon LLM Agents LLM Agent Planning Graph-Based Agent Memory

Mar 24, 2026

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model could select and execute a correct single tool call. As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such as safety, cost, and verifiability. We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area. First, we unify task formulations and distinguish single-call tool use from long-horizon orchestration. Then, we organize the literature around six core dimensions: inference-time planning and execution, training and trajectory construction, safety and control, efficiency under resource constraints, capability completeness in open environments, and benchmark design and evaluation. We further summarize representative applications in software engineering, enterprise workflows, graphical user interfaces, and mobile systems. Finally, we discuss major challenges and outline future directions for building reliable, scalable, and verifiable multi-tool agents.

Haoyuan Xu, Chang Li, Xinyan Ma +12

Harbin Institute of Technology, China · Harvard University, USA · Huawei Technologies Co., Ltd., China

LLM Tool Use Long-Horizon LLM Agents LLM Agent Planning LLM Agent Safety

Mar 23, 2026

OpenEarth-Agent: From Tool Calling to Tool Creation for Open-Environment Earth Observation

Earth Observation (EO) is essential for perceiving dynamic land surface changes, yet deploying autonomous EO in open environments is hindered by the immense diversity of multi-source data and heterogeneous tasks. While remote sensing agents have emerged to streamline EO workflows, existing tool-calling agents are confined to closed environments. They rely on pre-defined tools and are restricted to narrow scope, limiting their generalization to the diverse data and tasks. To overcome these limitations, we introduce OpenEarth-Agent, the first tool-creation agent framework tailored for open-environment EO. Rather than calling predefined tools, OpenEarth-Agent employs adaptive workflow planning and tool creation to generalize to unseen data and tasks. This adaptability is bolstered by an open-ended integration of multi-stage tools and cross-domain knowledge bases, enabling robust execution in the entire EO pipeline across multiple application domains. To comprehensively evaluate EO agents in open environments, we propose OpenEarth-Bench, a novel benchmark comprising 596 real-world, full-pipeline cases across seven application domains, explicitly designed to assess agents' adaptive planning and tool creation capabilities. Only essential pre-trained model tools are provided in this benchmark, devoid of any other predefined task-specific tools. Extensive experiments demonstrate that OpenEarth-Agent successfully masters full-pipeline EO across multiple domains in the open environment. Notably, on the cross-benchmark Earth-Bench, our tool-creating agent equipped with 6 essential pre-trained models achieves performance comparable to tool-calling agents relying on 104 specialized tools, and significantly outperforms them when provided with the complete toolset. In several cases, the created tools exhibit superior robustness to data anomalies compared to human-engineered counterparts.

Sijie Zhao, Feng Liu, Xueliang Zhang +11

Nanjing University · Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University +1

LLM Agent Tool Generation LLM Agent Planning Remote Sensing Benchmarks

Mar 19, 2026

PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents

Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordinating tools and guiding execution over local environments. In many deployments, however, the environment being planned over is private, containing source code, files, credentials, and metadata that cannot be exposed to the cloud. Existing solutions address adjacent concerns, such as execution isolation, access control, or confidential inference, but they do not control what cloud planners observe during planning: within the permitted scope, raw environment state is still exposed. We introduce PlanTwin, a privacy-preserving architecture for cloud-assisted planning without exposing raw local context. The key idea is to project the real environment into a planning-oriented digital twin: a schema-constrained and de-identified abstract graph that preserves planning-relevant structure while removing reconstructable details. The cloud planner operates solely on this sanitized twin through a bounded capability interface, while a local gatekeeper enforces safety policies and cumulative disclosure budgets. We further formalize the privacy-utility trade-off as a capability granularity problem, define architectural privacy goals using

(k,δ)

-anonymity and

ε

-unlinkability, and mitigate compositional leakage through multi-turn disclosure control. We implement PlanTwin as middleware between local agents and cloud planners and evaluate it on 60 agentic tasks across ten domains with four cloud planners. PlanTwin achieves full sensitive-item non-disclosure (SND = 1.0) while maintaining planning quality close to full-context systems: three of four planners achieve PQS

> 0.79

, and the full pipeline incurs less than 2.2% utility loss.

Guangsheng Yu, Qin Wang, Rui Lang +2

University of Technology Sydney · CSIRO Data61, Australia

AI Agent Security LLM Agent Planning Digital Twins Tool Access Control for LLM Agents

Mar 16, 2026

AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback

With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or low-level manipulation. In the landscape of embodied AI benchmarks, AsgardBench targets the capability category of interactive planning, which is more sophisticated than offline high-level planning as it requires agents to revise plans in response to environmental feedback, yet remains distinct from low-level execution. Unlike prior embodied AI benchmarks that conflate reasoning with navigation or provide rich corrective feedback that substitutes for perception, AsgardBench restricts agent input to images, action history, and lightweight success/failure signals, isolating interactive planning in a controlled simulator without low-level control noise. The benchmark contains 108 task instances spanning 12 task types, each systematically varied through object state, placement, and scene configuration. These controlled variations create conditional branches in which a single instruction can require different action sequences depending on what the agent observes, emphasizing conditional branching and plan repair during execution. Our evaluations of leading vision language models show that performance drops sharply without visual input, revealing weaknesses in visual grounding and state tracking that ultimately undermine interactive planning. Our benchmark zeroes in on a narrower question: can a model actually use what it sees to adapt a plan when things do not go as expected?

Andrea Tupini, Lars Liden, Reuben Tan +2

Microsoft Research

AI Agent Benchmarks LLM Agent Planning Robot Task Planning VLMs for Robotics Visually Grounded Reasoning

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

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.

Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair +6

ServiceNow Research · Mila - Quebec AI Institute · Université de Montréal

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

Mar 13, 2026

AI Planning Framework for LLM-Based Web Agents

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how they plan. This paper addresses this gap by formally treating web tasks as sequential decision-making processes. We introduce a taxonomy that maps modern agent architectures to traditional planning paradigms: Step-by-Step agents to Breadth-First Search (BFS), Tree Search agents to Best-First Tree Search, and Full-Plan-in-Advance agents to Depth-First Search (DFS). This framework allows for a principled diagnosis of system failures like context drift and incoherent task decomposition. To evaluate these behaviors, we propose five novel evaluation metrics that assess trajectory quality beyond simple success rates. We support this analysis with a new dataset of 794 human-labeled trajectories from the WebArena benchmark. Finally, we validate our evaluation framework by comparing a baseline Step-by-Step agent against a novel Full-Plan-in-Advance implementation. Our results reveal that while the Step-by-Step agent aligns more closely with human gold trajectories (38% overall success), the Full-Plan-in-Advance agent excels in technical measures such as element accuracy (89%), demonstrating the necessity of our proposed metrics for selecting appropriate agent architectures based on specific application constraints.

Orit Shahnovsky, Rotem Dror

Faculty of Computer and Information Science, University of Haifa, Haifa, Israel

LLM Agent Planning Web Agents LLM Agent Evaluation Web Agent Benchmarks

Mar 12, 2026

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance.

Xing Zhang, Yanwei Cui, Guanghui Wang +7

AWS Generative AI Innovation Center · HSBC

Multi-Agent Orchestration LLM Agent Planning LLM Agent Verification

Mar 10, 2026

SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding

LM-based agents excel when given high-level action APIs but struggle to ground language into low-level control. Prior work has LLMs generate skills or reward functions for RL, but these one-shot approaches lack feedback to correct specification errors. We introduce SCALAR, a bidirectional framework coupling LLM planning with RL through a learned skill library. The LLM proposes skills with preconditions and effects; RL trains policies for each skill and feeds back execution results to iteratively refine specifications, improving robustness to initial errors. Pivotal Trajectory Analysis corrects LLM priors by analyzing RL trajectories; Frontier Checkpointing optionally saves environment states at skill boundaries to improve sample efficiency. On Craftax, SCALAR achieves 88.2% diamond collection, a 1.9x improvement over the best baseline, and reaches the Gnomish Mines 9.1% of the time where prior methods fail entirely.

Renos Zabounidis, Yue Wu, Simon Stepputtis +4

School of Computer Science, Carnegie Mellon University · Department of Mechanical Engineering, Virginia Tech

LLM-Guided RL LLM Agent Skill Learning LLM Agent Planning LLM Planning Hierarchical RL

Mar 7, 2026

Enhancing Web Agents with a Hierarchical Memory Tree

Large language model-based web agents have shown strong potential in automating web interactions through advanced reasoning and instruction following. While retrieval-based memory derived from historical trajectories enables these agents to handle complex, long-horizon tasks, current methods struggle to generalize across unseen websites. We identify that this challenge arises from the flat memory structures that entangle high-level task logic with site-specific action details. This entanglement induces a workflow mismatch in new environments, where retrieved contents are conflated with current web, leading to logically inconsistent execution. To address this, we propose Hierarchical Memory Tree (HMT), a structured framework designed to explicitly decouple logical planning from action execution. HMT constructs a three-level hierarchy from raw trajectories via an automated abstraction pipeline: the Intent level maps diverse user instructions to standardized task goals; the Stage level defines reusable semantic subgoals characterized by observable pre-conditions and post-conditions; and the Action level stores action patterns paired with transferable semantic element descriptions. Leveraging this structure, we develop a stage-aware inference mechanism comprising a Planner and an Actor. By explicitly validating pre-conditions, the Planner aligns the current state with the correct logical subgoal to prevent workflow mismatch, while the Actor grounds actions by matching the stored semantic descriptions to the target page. Experimental results on Mind2Web and WebArena show that HMT significantly outperforms flat-memory methods, particularly in cross-website and cross-domain scenarios, highlighting the necessity of structured memory for robust generalization of web agents.

Yunteng Tan, Zhi Gao, Xinxiao Wu

Beijing Institute of Technology, Beijing 100081, China

Web Agents LLM Agent Memory Hierarchical Memory LLM Agent Planning

Mar 6, 2026

Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation

Task planning, the problem of sequencing actions to reach a goal from an initial state, is a core capability requirement for autonomous robotic systems. Whether large language models (LLMs) can serve as viable planners alongside classical symbolic methods remains an open question. We present PyPDDLEngine, an open-source Planning Domain Definition Language (PDDL) simulation engine that exposes planning operations as LLM tool calls through a Model Context Protocol (MCP) interface. Rather than committing to a complete action sequence upfront, the LLM acts as an interactive search policy that selects one action at a time, observes each resulting state, and can reset and retry. We evaluate four approaches on 102 International Planning Competition (IPC) Blocksworld instances under a uniform 180-second budget: Fast Downward lama-first and seq-sat-lama-2011 as classical baselines, direct LLM planning (Claude Haiku 4.5), and agentic LLM planning via PyPDDLEngine. Fast Downward achieves 85.3% success. The direct and agentic LLM approaches achieve 63.7% and 66.7%, respectively, a consistent but modest three-percentage-point advantage for the agentic approach at

5.7\times

higher token cost per solution. Across most co-solved difficulty blocks, both LLM approaches produce shorter plans than seq-sat-lama-2011 despite its iterative quality improvement, a result consistent with training-data recall rather than generalisable planning. These results suggest that agentic gains depend on the nature of environmental feedback. Coding agents benefit from externally grounded signals such as compiler errors and test failures, whereas PDDL step feedback is self-assessed, leaving the agent to evaluate its own progress without external verification.

Kai Göbel, Pierrick Lorang, Patrik Zips +1

AIT Austrian Institute of Technology GmbH, Vienna, Austria

LLM Planning LLM Agent Planning Large Language Model-Based Robot Planning Symbolic Planning

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 2, 2026

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning & Action-planning), a benchmark that uniquely unifies time-evolving personal context with an interactive toolbox and complex user intents. Our event-driven pipeline generates 2,413 scenarios across four protagonists, grounded in longitudinal life events and annotated by referential, functional, and informational complexity. Evaluation of state-of-the-art models (e.g., Claude-4.5-Opus, DeepSeek-V3.2) reveals significant performance degradation under high-complexity conditions, with argument generation emerging as the primary bottleneck. These findings expose critical limitations in current agents' ability to ground reasoning within messy personal context and orchestrate reliable multi-step plans. We release ASTRA-bench with a full execution environment and evaluation scripts to provide a diagnostic testbed for developing truly context-aware AI assistants.

Zidi Xiu, David Q. Sun, Kevin Cheng +9

Apple

Tool-Use Evaluation AI Agent Benchmarks LLM Agent Planning Personal AI Agents LLM Context Management

Mar 1, 2026

SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution

Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context management for accurate localization, and (2) systematic approaches for iterative, test-driven code modification to resolve issues. To address these challenges, we propose SWE-Adept, an LLM-based two-agent framework where a localization agent identifies issue-relevant code locations and a resolution agent implements the corresponding fixes. For issue localization, we introduce agent-directed depth-first search that selectively traverses code dependencies. This minimizes issue-irrelevant content in the agent's context window and improves localization accuracy. For issue resolution, we employ adaptive planning and structured problem solving. We equip the agent with specialized tools for progress tracking and Git-based version control. These tools interface with a shared working memory that stores code-state checkpoints indexed by execution steps, facilitating precise checkpoint retrieval. This design enables reliable agent-driven version-control operations for systematic issue resolution, including branching to explore alternative solutions and reverting failed edits. Experiments on SWE-Bench Lite and SWE-Bench Pro demonstrate that SWE-Adept consistently outperforms prior approaches in both issue localization and resolution, improving the end-to-end resolve rate by up to 4.3%.

Kang He, Kaushik Roy

Electrical and Computer Engineering, Purdue University

Code Localization Multi-Agent Coding Automated Program Repair Repository-Level Code Generation LLM Agent Planning Memory-Augmented Language Model Agents

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 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 24, 2026

SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery

Qualitative insights from user experiences are critical for informing product and policy decisions, but collecting such data at scale is constrained by the time and availability of experts to conduct semi-structured interviews. Recent work has explored using large language models (LLMs) to automate interviewing, yet existing systems lack a principled mechanism for balancing systematic coverage of predefined topics with adaptive exploration, or the ability to pursue follow-ups, deep dives, and emergent themes that arise organically during conversation. In this work, we formulate adaptive semi-structured interviewing as an optimization problem over the interviewer's behavior. We define interview utility as a trade-off between coverage of a predefined interview topic guide, discovery of relevant emergent themes, and interview cost measured by length. Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility. We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility, improving topic guide coverage (+4.7% over the best baseline) and eliciting richer emergent insights while using fewer conversational turns than prior LLM interviewing approaches. We further validate SparkMe in a user study with 70 participants across 7 professions on the impact of AI on their workflows. Domain experts rate SparkMe as producing high-quality adaptive interviews that surface helpful profession-specific insights not captured by prior approaches. The code, datasets, and evaluation protocols for SparkMe are available as open-source at https://github.com/SALT-NLP/SparkMe.

David Anugraha, Vishakh Padmakumar, Diyi Yang

Stanford University

LLM Agent Planning Multi-Agent LLM Systems