Pith. sign in

Paper Citation Record · LEDGER

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning

As of 13 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2608.07905.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.07905 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:47:48.648554Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

51 of 51 outbound references displayed

  • verified exact2
  • verified fuzzy24
  • unresolved25
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d0d2ef7b-364e-4d66-b04f-60f0462db2ae · outbound

This paper cites VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.475113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.475113Z digest=sha256:52089cbc12a3057abf2b1c264f22edd744f6ddb281bbd33d2d25de992fa88019

Observation 097511db-190b-4f7e-8bd2-a90f9e37e9d7 · outbound

This paper cites Online Continual Learning For Interactive Instruction Following Agents.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Online Continual Learning For Interactive Instruction Following Agents

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.479233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.479233Z digest=sha256:b3082d443633a816acf3563ce2a72783d3e91384b18c9594d2cdd40f84e9803f

Observation f08937cc-b295-4d44-b2b2-66d90af0f2d7 · outbound

This paper cites Realfred: An embodied instruction following benchmark in photo-realistic environ- ments,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Realfred: An embodied instruction following benchmark in photo-realistic environ- ments,

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.299953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.483300Z digest=sha256:3f9fdaf99981e3a767e6ed18c277f36ec42c299cacfa25962ee0cd54b55765e2

Observation 4aceb509-dd17-4f70-8f1c-9035a34f0944 · outbound

This paper cites CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.486961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.486961Z digest=sha256:8f1c5b884c3b85f31a1453cb540057c39982c4fb014595dbf20f7f3508847766

Observation ff889581-33ff-4bc6-b911-d5d92e7f1e10 · outbound

This paper cites Episodic transformer for vision- and-language navigation,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Episodic transformer for vision- and-language navigation,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.287451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.490925Z digest=sha256:99ed15c6490132201a795fbecc6bb0e96b15bcd770958dc7f03a1d0158700e51

Observation 9b2fd8d0-111a-40bf-bf0b-052e3e872603 · outbound

This paper cites Look wide and interpret twice: Improving performance on interactive instruction-following tasks,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Look wide and interpret twice: Improving performance on interactive instruction-following tasks,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.276738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.494194Z digest=sha256:6ef0a1d86f05c945f3b38422bcea0e8522d03de5ecf48d0d627bc1c62a3b017b

Observation 261e35c5-8818-4eb4-ba0e-c06c54249edc · outbound

This paper cites Spoc: Imitating shortest paths in simulation enables effective navigation and manipulation in the real world,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Spoc: Imitating shortest paths in simulation enables effective navigation and manipulation in the real world,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.255065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.501457Z digest=sha256:6dde918a1ee72dee57a844b2e6113b24e0a136ab7acf0ae64af8a60dcb58ef77

Observation 19897148-1787-4388-9560-2298d77a535c · outbound

This paper cites FILM: Following Instructions in Language with Modular Methods.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning FILM: Following Instructions in Language with Modular Methods

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.505126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.505126Z digest=sha256:064aa06a6ee3f9abb26ecac77ded1be3b02ab796ee69a7589bdcc7a359cd62d6

Observation 3ed32068-53fd-4fe5-b5fc-aefbfdfd90f9 · outbound

This paper cites Multi-level compositional reason- ing for interactive instruction following,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Multi-level compositional reason- ing for interactive instruction following,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.243112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.508888Z digest=sha256:c3c0fa755f40ad641d17b77bb7dab2d88b7dfb5291bffc03a46b3ce0bc10317c

Observation 96d588f2-abab-42cb-8691-b49ed2a0e5b1 · outbound

This paper cites Disco: Embodied navigation and interaction via differentiable scene semantics and dual-level control,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Disco: Embodied navigation and interaction via differentiable scene semantics and dual-level control,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.232017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.512206Z digest=sha256:62a8257ccd5e7222ab7cb61465d3dc9a7fb35904d80d0d08e8ed6ed0ee7c5281

Observation ce783213-92ad-4999-a78b-b8dc0fdcf13c · outbound

This paper cites Multi-modal grounded planning and efficient replanning for learning embodied agents with a few examples,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Multi-modal grounded planning and efficient replanning for learning embodied agents with a few examples,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.220293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.516021Z digest=sha256:c76f4bbd0a4e63733c924bf2ea41554e626f38c57c9707159d363225c0dcc09a

Observation 9211e4e5-769e-4daf-8915-e15f3c6ea373 · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.519648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.519648Z digest=sha256:c0514d7004585e20d1b3e89d75c63e9a8c2bd746b374bc3821d6a9ec9b46bcfd

Observation c8d4faaa-b1d5-44dc-b4e2-70b1d7e05ae6 · outbound

This paper cites Progprompt: Generating situated robot task plans using large language models,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Progprompt: Generating situated robot task plans using large language models,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.209319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.523776Z digest=sha256:7e59344739ba3d47323b0cade33dc6b91ab8640cd94f15658ec59cf5b95c009b

Observation 41ea833f-6e46-4057-a296-2890e5da0bd5 · outbound

This paper cites SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.527188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.527188Z digest=sha256:69defb96065cb608f56f8e28772736b649f2fe5f09aee922dd84225710ceebb6

Observation 01061845-751c-4e3a-967b-be16511eb7d8 · outbound

This paper cites Retrieval- augmented hierarchical in-context reinforcement learning and hindsight modular reflections for task planning with llms,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Retrieval- augmented hierarchical in-context reinforcement learning and hindsight modular reflections for task planning with llms,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.198102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.531206Z digest=sha256:589350af0fd59d1db850dad1fb39f566c392e87674f54821d3312f508f7bc7f1

Observation cc713381-aa14-43c9-ba4e-d6625d3b38c3 · outbound

This paper cites Llm-planner: Few-shot grounded planning for embodied agents with large language models,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Llm-planner: Few-shot grounded planning for embodied agents with large language models,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.534462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.534462Z digest=sha256:7d9990b289cfe44c28d5b73cceb2be82b9f774d4058a0512396ac91003105c16

Observation 3d9d7972-b518-4dc1-a6ca-5bf97eab3cd7 · outbound

This paper cites Robogpt: an llm-based long-term decision-making embodied agent for instruction following tasks,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Robogpt: an llm-based long-term decision-making embodied agent for instruction following tasks,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.180059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.538052Z digest=sha256:9ddfcc00bccb30abdf9e3ae78a939ff56e83f203232a91b1b7fc626d96a577e8

Observation 25526fee-3c77-4d3f-8a6f-3f50501e6b85 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.541443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.541443Z digest=sha256:9069ffc47ccd5f76fddbfeb2b40d7661d6cbb228b1b89f1b71c09d5228183cc2

Observation e67615b0-134b-46f4-976b-52d56417ca08 · outbound

This paper cites Concept- graphs: Open-vocabulary 3d scene graphs for perception and planning,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Concept- graphs: Open-vocabulary 3d scene graphs for perception and planning,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.545251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.545251Z digest=sha256:8b1b11f59913a6a38aac713a92c6c14cfb5faac7884ac643853734418b214f11

Observation c2263949-9ed6-40f3-bd58-f43fd505acb7 · outbound

This paper cites Search3d: Hierarchical open-vocabulary 3d segmentation,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Search3d: Hierarchical open-vocabulary 3d segmentation,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.162651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.548120Z digest=sha256:5a8cecb53514c41266ef49f2def7646d2944c3347b020886939bd6bbd5172108

Observation 0203bbce-bcb4-4177-b53b-62e071c6a532 · outbound

This paper cites Alfred: A benchmark for interpret- ing grounded instructions for everyday tasks,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Alfred: A benchmark for interpret- ing grounded instructions for everyday tasks,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.550907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.550907Z digest=sha256:1f1b07f38af82f9a2138c954e8c98e55e831c857a017fcd7f98628e0f339aa2c

Observation 987d1740-c82e-4f82-81cf-ad978394988e · outbound

This paper cites AI2-THOR: An Interactive 3D Environment for Visual AI.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning AI2-THOR: An Interactive 3D Environment for Visual AI

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.553706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.553706Z digest=sha256:f846948dde6b9f028febf05e1095f073dc4ac3b5badaad94a51ba627fa2de12e

Observation 4c18270b-a053-4719-ae04-441b272dc779 · outbound

This paper cites Virtualhome: Simulating household activities via programs,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Virtualhome: Simulating household activities via programs,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.145310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.556689Z digest=sha256:36c51f5f51739ed41bf82a1a48fbe3e5d9d8111a23e416bba3736ac56ebc2454

Observation cc968a3d-ea2b-4290-a501-c35834493128 · outbound

This paper cites Factorizing perception and policy for interactive instruction following,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Factorizing perception and policy for interactive instruction following,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.134008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.559625Z digest=sha256:14a85699fd13c5e9bbe30269a9ca935c0d1d5e2e5c957c47bfdc5d2c3e17c9ab

Observation 4cfc3c25-8ebc-4d17-80c5-34f46da38fe3 · outbound

This paper cites Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.562595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.562595Z digest=sha256:08781410832b8b5d3dd4707172ad67a6586e587da04b47956461d2a590bcb68d

Observation fc223705-0346-4bb0-919b-594f2709df37 · outbound

This paper cites OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.566019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.566019Z digest=sha256:fa79b2e1d2145ccf394988a53f0e81d73860224ef3bdbd7d11abf7358810cde0

Observation 83617d46-7322-4115-a466-e7d9c738fe5a · outbound

This paper cites Epo: Hierarchical llm agents with environment preference optimization,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Epo: Hierarchical llm agents with environment preference optimization,

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.122913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.569823Z digest=sha256:1903f8f635b6e32a019399e6a295ea32c2de4fd64bffad2390e2a95acd5e8a45

Observation d5c3009e-8120-4e83-9282-01c1000b1e71 · outbound

This paper cites Inner Monologue: Embodied Reasoning through Planning with Language Models.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Inner Monologue: Embodied Reasoning through Planning with Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.573045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.573045Z digest=sha256:b0046a2a289a0575a1c3cf388855881665f9bf89f2dc45cc01ecda64a2561283

Observation 0e01dfef-7f99-4582-ac15-a8c76216413c · outbound

This paper cites Pre-emptive action revision by environmental feedback for embodied instruction following agents,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Pre-emptive action revision by environmental feedback for embodied instruction following agents,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.111624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.576332Z digest=sha256:134a0d14240bef6d319bb8666de6ec06f2d5d14532201e93765a0bde9989679c

Observation f51d8f40-374e-4ad3-b038-f7d26678e9ff · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Chain-of-thought prompting elicits reasoning in large language models,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.579665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.579665Z digest=sha256:cf048a77ec737d811b8a7d58ddcc47a309a4f300b3c8916d7a989ab083f97396

Observation 8463d740-1e12-4a8b-8e78-c3853a453d0b · outbound

This paper cites Unsupervised explanation generation via correct instantiations,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Unsupervised explanation generation via correct instantiations,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.094036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.582846Z digest=sha256:93d9e9726904f7bdf45a7edfb14ff88b2e6eb9437cf9be7084705995613b3563

Observation 4092e538-ef9d-45c2-affc-38bbcb983d81 · outbound

This paper cites SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.585899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.585899Z digest=sha256:67b2a99b1cc01770dfd330bb26df560cd6c9aeb71957fb7f8bb82d63513cdc31

Observation 3da8dd71-e0a2-453e-9b50-dd5736c365ec · outbound

This paper cites Self-refine: Iter- ative refinement with self-feedback,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Self-refine: Iter- ative refinement with self-feedback,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.589207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.589207Z digest=sha256:d8f18b41b257d9fd8e9f6e44ae92062ae459800afa785a86a253a01d26df68bd

Observation 5a03c1ac-902d-432b-b325-8d25285e75b3 · outbound

This paper cites Amor: A recipe for building adaptable modular knowledge agents through process feedback,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Amor: A recipe for building adaptable modular knowledge agents through process feedback,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.074584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.592591Z digest=sha256:7faf916924b6de7edd7782ef05c7981238bc0ea3c95fa2dd3f2a365c29bf5c0a

Observation 901eea8f-723f-46ce-b3e3-685bfab70ad6 · outbound

This paper cites P-rag: Progressive retrieval augmented generation for planning on embodied everyday task,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning P-rag: Progressive retrieval augmented generation for planning on embodied everyday task,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.062429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.596209Z digest=sha256:0d4a9b3680021eda128b1bce87b1987d4414c231cf02f56e68c140cd096f616d

Observation d201aab4-5bd2-4101-97cf-ee2dab6f87f3 · outbound

This paper cites Instructrag: Leveraging retrieval-augmented generation on instruction graphs for llm-based task planning,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Instructrag: Leveraging retrieval-augmented generation on instruction graphs for llm-based task planning,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.049396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.599511Z digest=sha256:4a3252cc6898eea056484254d191a367250e5ba0a18a31482343d98c273ce536

Observation 8f647854-c1e0-42d2-8e5f-05bde973edd9 · outbound

This paper cites Double-feedback: Enhancing large language models reasoning in robotic tasks by knowl- edge graphs,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Double-feedback: Enhancing large language models reasoning in robotic tasks by knowl- edge graphs,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.037770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.602700Z digest=sha256:eec92ab9558b7420f47e1091605c41fcc3e6a416f6f7ebe5c608b3cfdcaab6f0

Observation b307ba83-8b47-42f2-8761-40c328dcc2d7 · outbound

This paper cites Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering

Reference 38

Resolution
verified exact
local_arxiv, observed 2026-08-12T00:47:48.843230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.605911Z digest=sha256:737ffd89f3e2924ef6eb46ca4dcbc0311874a9eadab13b423223ab9407f7521d

Observation 90af5c98-51e6-4d22-9217-44fbebef610b · outbound

This paper cites You Only Look at Screens: Multimodal Chain-of-Action Agents.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning You Only Look at Screens: Multimodal Chain-of-Action Agents

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.609892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.609892Z digest=sha256:236dd606df72a43363331df3f88270d47be292a85d0b9a9198a23bdfd3f74cd8

Observation f1b0ec0f-27ce-48df-b549-8261ed1d4d20 · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning ToolRL: Reward is All Tool Learning Needs

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.613693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.613693Z digest=sha256:bd98dbb82d3cd583713e15c5019d88ea58509a6622739aced1d2cc33ad89dd0f

Observation 7f819eed-dbc1-40c0-8d3d-1f4203d7de1a · outbound

This paper cites What is the Alignment Objective of GRPO?.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning What is the Alignment Objective of GRPO?

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.617633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.617633Z digest=sha256:0c681e885a26fc2804a62cb89d343a59fac4347e3b8d66527c80c3223c7be0da

Observation 7833ba14-7d2e-44b4-aa7b-f411030cef2d · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.621352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.621352Z digest=sha256:f522b5e17655e309311ceb93bfa7ef11a567b357c1172cddddd3c94b725e9091

Observation b20bfa9a-b1e3-402a-af2e-40ce9f073a59 · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.625599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.625599Z digest=sha256:9d2cb72fc69be81c2faa24b6ce941d5783933361ddfd8ad2edbfc4fda1b11bc5

Observation ebe04acd-e761-477a-a583-c27d6e287ea0 · outbound

This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.629467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.629467Z digest=sha256:0160ab70a6d7e3b704c24df3b35548aa3955e7b252051aa90aa72e150773459a

Observation 37b5f39e-e1f5-4f56-a772-f53cbbf9c871 · outbound

This paper cites Context-aware planning and environment-aware memory for instruction following embodied agents,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Context-aware planning and environment-aware memory for instruction following embodied agents,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-12T00:47:48.633427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:47:48.633427Z digest=sha256:ab8d20f4798aa391b4f718b7633865814c9d196926719aadd5a3ad8b2248801c

Observation 26012b19-aedd-4e8f-bf63-afb9a269e349 · outbound

This paper cites One demo is all it takes: Planning domain derivation with llms from a single demonstration,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning One demo is all it takes: Planning domain derivation with llms from a single demonstration,

Reference 46

Resolution
verified exact
raw_fallback, observed 2026-08-12T00:47:48.763199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.636526Z digest=sha256:fa2d5cb7af504a4194059ae9f0f04f7fa75b8382d6f3da4b27bb0fef76b25678

Observation f779d019-8ba7-4b89-aed3-a182c595eace · outbound

This paper cites A persistent spatial semantic representation for high-level natural language instruction exe- cution,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning A persistent spatial semantic representation for high-level natural language instruction exe- cution,

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.018980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.639579Z digest=sha256:7d56a26e50a1ce2fcd6b5264854a57552b12d023e0b9a05040f3abf97ed37969

Observation 7d67d89b-f2a4-4d0a-b62a-a5cc07b581ee · outbound

This paper cites Lota-bench: Benchmarking language-oriented task planners for embodied agents,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Lota-bench: Benchmarking language-oriented task planners for embodied agents,

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:49.007464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.642672Z digest=sha256:4dfc51bc199b91de81097b7968850354a17b021b3dd9df4f21019cca7083fe46

Observation fd4d0c53-7b4a-4c2d-bb6b-218ef9dd1a32 · outbound

This paper cites Lifelong experience abstraction and planning,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Lifelong experience abstraction and planning,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:48.995842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.645654Z digest=sha256:9e23eaa3ed1408d4e69f6416e1e6c815ed6520a0b0824068df48481f908477e0

Observation da251454-6a79-4932-a832-66ecafdcb0b6 · outbound

This paper cites Embodied agent interface: Benchmarking llms for embodied decision making,.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Embodied agent interface: Benchmarking llms for embodied decision making,

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:47:48.984896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.648554Z digest=sha256:7741fb3ab6a023926c86eac2dfa3d5151a0bfa5ca8697a07554df9213ee18ba5

Observation 2707230e-bcb0-4d21-b77e-2094ef24476b · outbound

This paper cites an unresolved cited work.

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning Unresolved cited work

Reference 2021

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:47:49.266645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T00:47:48.497777Z digest=sha256:53f676c733f0a9ce48fff542ecd433db6428b37efcc853493e07af6032655692

Pith citing papers

No inbound Pith citation observations are available.