{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/task-planning/papers/2","list_of":"/task/task-planning","task":"Task Planning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"of":344,"counts":{"archive_papers_tagged":344,"with_a_code_link":100,"where_syntology_ran_a_sample":35,"not_listed_spam_title":0,"listed":344,"listed_where_code_ran":35,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/task-planning","prev":"/task/task-planning","next":"/task/task-planning/papers/3","papers":[{"url":null,"slug":"medprompt-llm-cnn-fusion-with-weight-routing","title":"MedPrompt: LLM-CNN Fusion with Weight Routing for Medical Image Segmentation and Classification","date":"2025-06-26","arxiv_id":"2506.21199","repositories_listed":0,"syntology":null},{"url":null,"slug":"vla-os-structuring-and-dissecting-planning","title":"VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17561","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-fused-learning-for-solving-the","title":"Multimodal Fused Learning for Solving the Generalized Traveling Salesman Problem in Robotic Task Planning","date":"2025-06-20","arxiv_id":"2506.16931","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-ai-search-paradigm","title":"Towards AI Search Paradigm","date":"2025-06-20","arxiv_id":"2506.17188","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirage-1-augmenting-and-updating-gui-agent","title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","date":"2025-06-12","arxiv_id":"2506.10387","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-09049","title":"VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning","date":"2025-06-10","arxiv_id":"2506.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-vision-planner-and-executor-for-text","title":"Language-Vision Planner and Executor for Text-to-Visual Reasoning","date":"2025-06-09","arxiv_id":"2506.07778","repositories_listed":0,"syntology":null},{"url":"/paper/robopara-dual-arm-robot-planning-with","slug":"robopara-dual-arm-robot-planning-with","title":"RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks","date":"2025-06-07","arxiv_id":"2506.06683","repositories_listed":0,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robopara-dual-arm-robot-planning-with#ran","syntology_url":"https://syntology.ai/paper/2506.06683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.06683"}},"official":null}},{"url":null,"slug":"hierarchical-debate-based-large-language","title":"Hierarchical Debate-Based Large Language Model (LLM) for Complex Task Planning of 6G Network Management","date":"2025-06-06","arxiv_id":"2506.06519","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-physical-properties-of-unseen","title":"Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions","date":"2025-06-04","arxiv_id":"2506.03760","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-06363","title":"ChemGraph: An Agentic Framework for Computational Chemistry Workflows","date":"2025-06-03","arxiv_id":"2506.06363","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-vision-language-interpreter-for","title":"Grounded Vision-Language Interpreter for Integrated Task and Motion Planning","date":"2025-06-03","arxiv_id":"2506.03270","repositories_listed":0,"syntology":null},{"url":null,"slug":"tru-pomdp-task-planning-under-uncertainty-via","title":"Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs","date":"2025-06-03","arxiv_id":"2506.02860","repositories_listed":0,"syntology":null},{"url":null,"slug":"lohovla-a-unified-vision-language-action","title":"LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks","date":"2025-05-31","arxiv_id":"2506.00411","repositories_listed":0,"syntology":null},{"url":null,"slug":"master-multi-agent-security-through","title":"MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework","date":"2025-05-24","arxiv_id":"2505.18572","repositories_listed":0,"syntology":null},{"url":null,"slug":"robo2vlm-visual-question-answering-from-large","title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets","date":"2025-05-21","arxiv_id":"2505.15517","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-a-stable-planner-an-extended-finite","title":"Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent","date":"2025-05-20","arxiv_id":"2505.14141","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10872","title":"REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?","date":"2025-05-16","arxiv_id":"2505.10872","repositories_listed":0,"syntology":null},{"url":null,"slug":"lodge-joint-hierarchical-task-planning-and","title":"LODGE: Joint Hierarchical Task Planning and Learning of Domain Models with Grounded Execution","date":"2025-05-15","arxiv_id":"2505.13497","repositories_listed":0,"syntology":null},{"url":null,"slug":"pipa-a-unified-evaluation-protocol-for","title":"PIPA: A Unified Evaluation Protocol for Diagnosing Interactive Planning Agents","date":"2025-05-02","arxiv_id":"2505.01592","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordfield-coordination-field-for-agentic-uav","title":"CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios","date":"2025-04-30","arxiv_id":"2505.00091","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-pre-trained-large-language-models-1","title":"Leveraging Pre-trained Large Language Models with Refined Prompting for Online Task and Motion Planning","date":"2025-04-30","arxiv_id":"2504.21596","repositories_listed":0,"syntology":null},{"url":null,"slug":"nora-a-small-open-sourced-generalist-vision","title":"NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks","date":"2025-04-28","arxiv_id":"2504.19854","repositories_listed":0,"syntology":null},{"url":null,"slug":"robo-troj-attacking-llm-based-task-planners","title":"Robo-Troj: Attacking LLM-based Task Planners","date":"2025-04-23","arxiv_id":"2504.17070","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-benchmarking-and-aligning","title":"A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents","date":"2025-04-20","arxiv_id":"2504.14650","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructrag-leveraging-retrieval-augmented","title":"InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning","date":"2025-04-17","arxiv_id":"2504.13032","repositories_listed":0,"syntology":null},{"url":null,"slug":"findanything-open-vocabulary-and-object","title":"FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment","date":"2025-04-11","arxiv_id":"2504.08603","repositories_listed":0,"syntology":null},{"url":null,"slug":"personality-driven-decision-making-in-llm","title":"Personality-Driven Decision-Making in LLM-Based Autonomous Agents","date":"2025-04-01","arxiv_id":"2504.00727","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-environment-interactive-planning-for","title":"Visual Environment-Interactive Planning for Embodied Complex-Question Answering","date":"2025-04-01","arxiv_id":"2504.00775","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-interactive-navigation-of-quadruped","title":"Adaptive Interactive Navigation of Quadruped Robots using Large Language Models","date":"2025-03-29","arxiv_id":"2503.22942","repositories_listed":0,"syntology":null},{"url":null,"slug":"remac-self-reflective-and-self-evolving-multi","title":"REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation","date":"2025-03-28","arxiv_id":"2503.22122","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-application-system-in-office","title":"Multi-agent Application System in Office Collaboration Scenarios","date":"2025-03-25","arxiv_id":"2503.19584","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-spatial-perception-by-building","title":"Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs","date":"2025-03-19","arxiv_id":"2503.15091","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-aware-task-planning-via-large-language","title":"Safety Aware Task Planning via Large Language Models in Robotics","date":"2025-03-19","arxiv_id":"2503.15707","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-3d-activity-reasoning-and-planning","title":"Exploring 3D Activity Reasoning and Planning: From Implicit Human Intentions to Route-Aware Planning","date":"2025-03-17","arxiv_id":"2503.12974","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-cross-modal-distraction-and","title":"Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided, Self-Consistent MLLMs for Food Preparation Task Planning","date":"2025-03-17","arxiv_id":"2503.13055","repositories_listed":0,"syntology":null},{"url":null,"slug":"being-0-a-humanoid-robotic-agent-with-vision","title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","date":"2025-03-16","arxiv_id":"2503.12533","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-modeling-makes-a-better-planner-dual","title":"World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning","date":"2025-03-13","arxiv_id":"2503.10480","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgicalvlm-agent-towards-an-interactive-ai","title":"SurgicalVLM-Agent: Towards an Interactive AI Co-Pilot for Pituitary Surgery","date":"2025-03-12","arxiv_id":"2503.09474","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-aerial-intelligent-agents","title":"General-Purpose Aerial Intelligent Agents Empowered by Large Language Models","date":"2025-03-11","arxiv_id":"2503.08302","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-effectiveness-of-a-socratic","title":"Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study","date":"2025-03-11","arxiv_id":"2503.08174","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrective-task-planning-by-inverse","title":"Self-Corrective Task Planning by Inverse Prompting with Large Language Models","date":"2025-03-10","arxiv_id":"2503.07317","repositories_listed":0,"syntology":null},{"url":null,"slug":"star-a-foundation-model-driven-framework-for","title":"STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems","date":"2025-03-08","arxiv_id":"2503.06060","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-retrospective-language-agents-via","title":"Improving Retrospective Language Agents via Joint Policy Gradient Optimization","date":"2025-03-03","arxiv_id":"2503.01490","repositories_listed":0,"syntology":null},{"url":null,"slug":"robobrain-a-unified-brain-model-for-robotic","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","date":"2025-02-28","arxiv_id":"2502.21257","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-preference-optimization-for-vision","title":"Structured Preference Optimization for Vision-Language Long-Horizon Task Planning","date":"2025-02-28","arxiv_id":"2502.20742","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapidpen-fully-automated-ip-to-shell","title":"RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents","date":"2025-02-23","arxiv_id":"2502.16730","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-and-secure-embodied-ai-a","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","date":"2025-02-18","arxiv_id":"2502.13175","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-autonomous-agents-via-automatic","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","date":"2025-02-17","arxiv_id":"2502.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"octotools-an-agentic-framework-with","title":"OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning","date":"2025-02-16","arxiv_id":"2502.11271","repositories_listed":0,"syntology":null},{"url":null,"slug":"stma-a-spatio-temporal-memory-agent-for-long","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","date":"2025-02-14","arxiv_id":"2502.10177","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-grounded-vision-language-framework-for","title":"3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning","date":"2025-02-13","arxiv_id":"2502.08903","repositories_listed":0,"syntology":null},{"url":null,"slug":"vote-tree-planner-optimizing-execution-order","title":"Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting","date":"2025-02-13","arxiv_id":"2502.09749","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-schema-guided-reason-while-retrieve","title":"A Schema-Guided Reason-while-Retrieve framework for Reasoning on Scene Graphs with Large-Language-Models (LLMs)","date":"2025-02-05","arxiv_id":"2502.03450","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-moe-a-mixture-of-experts-multi-modal-llm","title":"3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow","date":"2025-01-28","arxiv_id":"2501.16698","repositories_listed":0,"syntology":null},{"url":null,"slug":"physbench-benchmarking-and-enhancing-vision","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","date":"2025-01-27","arxiv_id":"2501.16411","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-robotic-manipulation-with-language","title":"Zero-shot Robotic Manipulation with Language-guided Instruction and Formal Task Planning","date":"2025-01-25","arxiv_id":"2501.15214","repositories_listed":0,"syntology":null},{"url":null,"slug":"divide-then-aggregate-an-efficient-tool","title":"Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation","date":"2025-01-21","arxiv_id":"2501.12432","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatialcot-advancing-spatial-reasoning","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","date":"2025-01-17","arxiv_id":"2501.10074","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-hierarchical-reinforcement-learning","title":"Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning","date":"2024-12-27","arxiv_id":"2412.19538","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-paragraph-is-all-it-takes-rich-robot","title":"A Paragraph is All It Takes: Rich Robot Behaviors from Interacting, Trusted LLMs","date":"2024-12-24","arxiv_id":"2412.18588","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphagent-agentic-graph-language-assistant","title":"GraphAgent: Agentic Graph Language Assistant","date":"2024-12-22","arxiv_id":"2412.17029","repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-of-code-a-hybrid-approach-for-robust","title":"Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution","date":"2024-12-18","arxiv_id":"2412.14212","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-an-llm-swarm-to-a-pddl-empowered-hive","title":"From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle","date":"2024-12-17","arxiv_id":"2412.12839","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontology-driven-prompt-tuning-for-llm-based","title":"Ontology-driven Prompt Tuning for LLM-based Task and Motion Planning","date":"2024-12-10","arxiv_id":"2412.07493","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypergraphos-a-meta-operating-system-for","title":"HyperGraphOS: A Meta Operating System for Science and Engineering","date":"2024-12-06","arxiv_id":"2412.04923","repositories_listed":0,"syntology":null},{"url":null,"slug":"datalab-a-unifed-platform-for-llm-powered","title":"DataLab: A Unified Platform for LLM-Powered Business Intelligence","date":"2024-12-03","arxiv_id":"2412.02205","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-to-sim-via-end-to-end-differentiable","title":"One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering","date":"2024-11-29","arxiv_id":"2412.00259","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-is-on-my-sight-scene-graph-filtering-for","title":"Time is on my sight: scene graph filtering for dynamic environment perception in an LLM-driven robot","date":"2024-11-22","arxiv_id":"2411.15027","repositories_listed":0,"syntology":null},{"url":null,"slug":"verigraph-scene-graphs-for-execution","title":"VeriGraph: Scene Graphs for Execution Verifiable Robot Planning","date":"2024-11-15","arxiv_id":"2411.10446","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-intelligent-healthcare-a","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","date":"2024-11-05","arxiv_id":"2411.03287","repositories_listed":0,"syntology":null},{"url":null,"slug":"textbf-emos-textbf-e-mbodiment-aware","title":"EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents","date":"2024-10-30","arxiv_id":"2410.22662","repositories_listed":0,"syntology":null},{"url":null,"slug":"fishnet-financial-intelligence-from-sub","title":"FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning","date":"2024-10-25","arxiv_id":"2410.19727","repositories_listed":0,"syntology":null},{"url":null,"slug":"visioncoder-empowering-multi-agent-auto","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","date":"2024-10-25","arxiv_id":"2410.19245","repositories_listed":0,"syntology":null},{"url":null,"slug":"vipact-visual-perception-enhancement-via","title":"VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use","date":"2024-10-21","arxiv_id":"2410.16400","repositories_listed":0,"syntology":null},{"url":null,"slug":"climb-language-guided-continual-learning-for","title":"CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building","date":"2024-10-17","arxiv_id":"2410.13756","repositories_listed":0,"syntology":null},{"url":null,"slug":"rescueadi-adaptive-disaster-interpretation-in","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","date":"2024-10-17","arxiv_id":"2410.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"at-moe-adaptive-task-planning-mixture-of","title":"AT-MoE: Adaptive Task-planning Mixture of Experts via LoRA Approach","date":"2024-10-12","arxiv_id":"2410.10896","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-see-robot-do-human-demo-video-to-robot","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","date":"2024-10-11","arxiv_id":"2410.08792","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptagent-llm-driven-precondition","title":"ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution","date":"2024-10-08","arxiv_id":"2410.06108","repositories_listed":0,"syntology":null},{"url":null,"slug":"et-plan-bench-embodied-task-level-planning","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","date":"2024-10-02","arxiv_id":"2410.14682","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamma-p-generalizable-multi-agent-long","title":"LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner","date":"2024-09-30","arxiv_id":"2409.20560","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-epistemic-human-aware-task-planner-which","title":"An Epistemic Human-Aware Task Planner which Anticipates Human Beliefs and Decisions","date":"2024-09-27","arxiv_id":"2409.18545","repositories_listed":0,"syntology":null},{"url":null,"slug":"karma-augmenting-embodied-ai-agents-with-long","title":"KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems","date":"2024-09-23","arxiv_id":"2409.14908","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignbot-aligning-vlm-powered-customized-task","title":"AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots","date":"2024-09-18","arxiv_id":"2409.11905","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-planning-from-multi-modal","title":"LEMMo-Plan: LLM-Enhanced Learning from Multi-Modal Demonstration for Planning Sequential Contact-Rich Manipulation Tasks","date":"2024-09-18","arxiv_id":"2409.11863","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-rag-progressive-retrieval-augmented","title":"P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task","date":"2024-09-17","arxiv_id":"2409.11279","repositories_listed":0,"syntology":null},{"url":null,"slug":"siftom-robust-spoken-instruction-following","title":"SIFToM: Robust Spoken Instruction Following through Theory of Mind","date":"2024-09-17","arxiv_id":"2409.10849","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-reusable-multi-robot-planning","title":"Encoding Reusable Multi-Robot Planning Strategies as Abstract Hypergraphs","date":"2024-09-16","arxiv_id":"2409.10692","repositories_listed":0,"syntology":null},{"url":null,"slug":"relevance-for-human-robot-collaboration","title":"Relevance for Human Robot Collaboration","date":"2024-09-12","arxiv_id":"2409.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-llms-graphs-and-object-hierarchies","title":"Scalable Task Planning via Large Language Models and Structured World Representations","date":"2024-09-07","arxiv_id":"2409.04775","repositories_listed":0,"syntology":null},{"url":null,"slug":"empower-embodied-multi-role-open-vocabulary","title":"EMPOWER: Embodied Multi-role Open-vocabulary Planning with Online Grounding and Execution","date":"2024-08-30","arxiv_id":"2408.17379","repositories_listed":0,"syntology":null},{"url":null,"slug":"aeroverse-uav-agent-benchmark-suite-for","title":"AeroVerse: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models","date":"2024-08-28","arxiv_id":"2408.15511","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-enhanced-scene-graph-learning-for","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","date":"2024-08-22","arxiv_id":"2408.12093","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-behavior-planning-for-humanoid","title":"Autonomous Behavior Planning For Humanoid Loco-manipulation Through Grounded Language Model","date":"2024-08-15","arxiv_id":"2408.08282","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-clothes-manipulation-with","title":"General-purpose Clothes Manipulation with Semantic Keypoints","date":"2024-08-15","arxiv_id":"2408.08160","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-with-code-comparing-approaches-for","title":"Plan with Code: Comparing approaches for robust NL to DSL generation","date":"2024-08-15","arxiv_id":"2408.08335","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-natural-language-understanding-for","title":"Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation","date":"2024-08-15","arxiv_id":"2408.08188","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-in-context-reinforcement","title":"Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs","date":"2024-08-12","arxiv_id":"2408.06520","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-planning-using-visual-language","title":"Multi-Agent Planning Using Visual Language Models","date":"2024-08-10","arxiv_id":"2408.05478","repositories_listed":0,"syntology":null}],"record_sha256":"c27c7a7668d932eaee4bcb3ed7c3b113ffe485febeb07dadcc80a54abd2774b2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}