Pith. sign in

Paper Citation Record · LEDGER

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation

As of 5 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2604.08232.

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

pith.paper-citation-record.v1
2604.08232 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:01:13.350219Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

49 of 49 outbound references displayed

  • verified exact35
  • verified fuzzy13
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 63e1bc91-870d-4aab-9d36-b2c641d5d677 · outbound

This paper cites Qwen2.5-VL Technical Report.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Qwen2.5-VL Technical Report

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.423245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:55f432caf1293d1e7b8141a292e2aa6ae1b87c07eb70e6f2019b279c399ddae6

Observation 08b80605-3bd9-4cba-b28e-621a1fb7e6cb · outbound

This paper cites ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.411519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d271326cdf426df9422fe750fd46e57b3334f0c1971879ca8739fffb3334b46f

Observation cc1ed114-7c05-414e-8919-0ff1995b280d · outbound

This paper cites CL-CoTNav: Closed-Loop Hierarchical Chain-of-Thought for Zero-Shot Object-Goal Navigation with Vision-Language Models.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation CL-CoTNav: Closed-Loop Hierarchical Chain-of-Thought for Zero-Shot Object-Goal Navigation with Vision-Language Models

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.449382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:c06298730ca322fd179fa58c2a2df12d4deae4ad98c25a0a11b639a3a54d260c

Observation 4de19eb7-4fa8-467a-bd95-81c8ee95b889 · outbound

This paper cites CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.420570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:99dd15435d66339105d21459b5fcef17189230824420020d00733266ea108415

Observation 62b25f82-9524-4443-8d54-8cf80a22a0a2 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Evaluating Large Language Models Trained on Code

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.474534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:8b21c01f746bd33b6b4413fa558ea23266da298aa7a1345aac195dca5eb73057

Observation 5e3b2393-90a8-4ea3-84f6-6ad3824b90c3 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-05-13T15:51:30.429014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:0e6d02660c5ecca5f2cc44f632351750759f0b3f7e8877e90f716785499b9fd7

Observation 36db350c-d7f4-4364-9154-3106a2bf5bec · outbound

This paper cites NaVILA: Legged Robot Vision-Language-Action Model for Navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation NaVILA: Legged Robot Vision-Language-Action Model for Navigation

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.469951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:dd5c878f5d326d2f47088dfae0ca57a728a3b1b8483b15a53e3d339791a321f2

Observation 18429ce5-426a-4ef9-a8d2-7b214ee8078c · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-05-12T12:31:34.026635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:60d4bf0401a036f4b75087a86eff3b2c21694971ee4c8a9840606b8ad2d6edd0

Observation df5a5ad9-33f6-41f3-a21b-ed4e07eee4a3 · outbound

This paper cites Gemini pro.https : / / deepmind.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Gemini pro.https : / / deepmind

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.478430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:a2480bc7526cd60420cfed0ff18d025db40ad04e6f65619aa020948e4ff57f7f

Observation b00d08bf-6cc8-444d-8e14-dee260877ed1 · outbound

This paper cites Agentic Reinforced Policy Optimization.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Agentic Reinforced Policy Optimization

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-17T02:57:12.173630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:697ed383a55caea5a495025ed2a1a2120cf9f121a1e33e99ce199ad289d2963c

Observation efdd11c8-de88-455b-a971-b8e8c227d687 · outbound

This paper cites Spoc: Imitating shortest paths in simulation enables effective navigation and manipu- lation in the real world.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Spoc: Imitating shortest paths in simulation enables effective navigation and manipu- lation in the real world

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.496978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:3c032e77a56f6520cd3c2b4dd6e994fccbbafa20f3797b97fe9b56983109d35f

Observation f80e300f-c6b9-416b-b621-1aa4cbd43176 · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Group-in-Group Policy Optimization for LLM Agent Training

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-11T09:15:09.492454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:15ba558b50595354bc8d5347e355d1a1d4e6296f2d4afa4d90feb7408315f3ea

Observation 85ef3596-fb15-40cf-9559-35a679db4d98 · outbound

This paper cites OctoNav: Towards Generalist Embodied Navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation OctoNav: Towards Generalist Embodied Navigation

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.482558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:25f219ab92e95efabc0a4527ead05f973074b4c53ef89157bd7c6aba2204f847

Observation bd9593b0-58f1-4a15-9728-2a66a9e90dc7 · outbound

This paper cites End-to-end navigation with vlms: Transforming spatial reasoning into question-answering.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation End-to-end navigation with vlms: Transforming spatial reasoning into question-answering

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.482697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d6f93cce228fe285573aadcd301b598c4916f65ffc2cbc850382cf0d906d87ba

Observation f3ceeba5-8c51-4baa-9fb4-098a2ce803bc · outbound

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

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 15

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.429460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:e336266b66aae5650a5809924ea28be36316cac5e400852bfcd9e41de12993af

Observation e3d19cdf-5c3e-4382-ba4d-4af72e717737 · outbound

This paper cites Mask r-cnn.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Mask r-cnn

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.492707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:88af6136aabdce8c9abc289c5b01b0257bc504f6c707cc9c364cf31fb9978d10

Observation 7c528cff-860c-4560-bd10-bc32b5f3906b · outbound

This paper cites Adactrl: Towards adaptive and controllable reasoning via difficulty-aware budgeting.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Adactrl: Towards adaptive and controllable reasoning via difficulty-aware budgeting

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.443893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:2e3d8cbd32a4853a0a7b0b1c0feccad4fe7f041036b69467e30ac842fa859365

Observation d1fa1cb3-c5a2-4fd3-80e8-8780c8c7a038 · outbound

This paper cites GPT-4o System Card.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation GPT-4o System Card

Reference 18

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.551303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:c72f74a08fa5540f83ff4276817ecc03624ad7c152bce1f36ea5674b50fcb75d

Observation 00073c2d-6880-4c3e-b99d-7a8d455b29fd · outbound

This paper cites Think Only When You Need with Large Hybrid-Reasoning Models.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Think Only When You Need with Large Hybrid-Reasoning Models

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.533819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d1229c42572289123f72dccf7557c04db79770382d376d96d1499e35b313b286

Observation 02f70e82-0b58-4b2b-bf95-09b97bf02c98 · outbound

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

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation AI2-THOR: An Interactive 3D Environment for Visual AI

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-05-12T05:24:31.084211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:c297d7a8062e3fe4227fcec3c89cc7ed0f0f7b870ee373c5dce5f7a90a70186a

Observation e8b36ae9-32b8-4ed6-add2-9d7cb0c6f4a1 · outbound

This paper cites Think or not think: A study of ex- plicit thinking in rule-based visual reinforcement fine-tuning.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Think or not think: A study of ex- plicit thinking in rule-based visual reinforcement fine-tuning

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.503518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:aca0bde0d4283471c573ab1b6bedba4d9192ac8344e47abf186bd8a237d4f346

Observation 0296e041-2ce1-42e6-8440-ba3edfd809e4 · outbound

This paper cites Introducing o3 and o4 mini.https://openai.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Introducing o3 and o4 mini.https://openai

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.502633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d575528913052a813c31c02df1de201f321c7bb555ae004ad2ff50f5cbb36d0f

Observation 4f77e5ab-a763-40d7-954b-5d6a99c677ee · outbound

This paper cites Training language models to follow instructions with human feedback.Ad- vances in neural information processing systems, 35:27730– 27744.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Training language models to follow instructions with human feedback.Ad- vances in neural information processing systems, 35:27730– 27744

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.506682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:ac3d28d54628c43dd0dd78fdd0ec290d32a71870ccbcb06a5d26c16da6a5c543

Observation 53443418-d67e-4f2a-9708-e9072ca1faf8 · outbound

This paper cites VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.531030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:37645c8d7053acc3b3ec70257dbf780a807881d258dbf7270f481d9a2651a2ea

Observation d0ab8b04-ac34-4f9d-b06b-43a90a7ca936 · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 25

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.494773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:219f1ae6b4699204c3560f3ec54fcc318e7c23831260c0149c8d69030eeeca49

Observation 4064bee8-9320-4d27-8d6e-9c97e29526ec · outbound

This paper cites Proximal Policy Optimization Algorithms.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Proximal Policy Optimization Algorithms

Reference 26

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.525911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:a5ce307bf4fe4a40bf0c60d656d4e12001ec2fa418c2cacb70de1f1f9ab8e764

Observation 8a93744f-be44-4058-897a-9d66728daf6f · outbound

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

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.543530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:c73541a1c275ec16a09b8e679f14e6c52309592822aa3b0746b7bfa419a09b2e

Observation d25c45e3-e423-4e68-90e2-b397ca482dc7 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-05-12T06:39:15.970362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:20c00f3ca606b3d42061d0844986797a3eef01e072678c888eef3ae3d5c4372c

Observation 2a9e2185-4594-4d1c-b9f4-061d0068d8cc · outbound

This paper cites To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.500506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:1bda3bcf4927dc7dd4c61920673d0993b11c70981690d8eec2aa6612f9e41a9b

Observation f79685de-cd48-4016-a07b-fffd5be3806d · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Gemini: A Family of Highly Capable Multimodal Models

Reference 30

Resolution
verified exact
local_arxiv, observed 2026-05-11T07:41:01.528363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:bf8ae68cbf7cf66591057e31265eb68a55be7998781fceacbd8c923e3d74c780

Observation a8c0ca0d-3c22-4af5-9d65-d5ef63f81c49 · outbound

This paper cites arXiv preprint arXiv:2505.10832 , year=.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation arXiv preprint arXiv:2505.10832 , year=

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.546310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:34295f8be2c84415c8861ff93380ba64f7b8ecbd1ac493b95f7625a40d31a723

Observation 5ff6525e-e181-4697-ab5a-3dd26dfa7094 · outbound

This paper cites Aux-think: Exploring reason- ing strategies for data-efficient vision-language navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Aux-think: Exploring reason- ing strategies for data-efficient vision-language navigation

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.553704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:e65a091ed2a508848b3f7b8db7efe514f5ad463c8ab81bcc694d6edf42f2375a

Observation ef9a0f5b-a448-4248-b8e4-5583497fbed7 · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-05-12T12:12:09.004283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d88d274d82e8cab9a6a6f6e454b7ce817ec2cf10e0829045b8659367295be785

Observation 21200471-a562-4351-a688-c395b73ac767 · outbound

This paper cites Adaptive Deep Reasoning: Triggering Deep Thinking When Needed.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Adaptive Deep Reasoning: Triggering Deep Thinking When Needed

Reference 34

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.509692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d8f55baa5df2e330d1281787f70bf0bc6dc8c53a0edf1d45ac7c83d23ad8d0a8

Observation 601315d0-e27a-42a8-a77c-0397f4d7778c · outbound

This paper cites DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.492076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:4bedf2a052fedda4cf7a1ec916db6104f51db6bdcc54bbc48c16cb368b9cb1b2

Observation fc482c90-0125-4e83-90f2-ae6117d69cf8 · outbound

This paper cites Q-learning.Ma- chine learning, 8(3):279–292.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Q-learning.Ma- chine learning, 8(3):279–292

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.521681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:730a5a17ad7761b3af3a9fd22768adc6250267deecee235e62eb45bd23ad80d9

Observation f4276774-44b5-4487-a6b3-f002448b8e70 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large lan- guage models.Advances in neural information processing systems, 35:24824–24837.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Chain-of-thought prompting elicits reasoning in large lan- guage models.Advances in neural information processing systems, 35:24824–24837

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.516054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d0081b230588d20e8d5135b584bb9c36cd5c172722f2c3ca07f794a02cbffbcb

Observation aa158978-914f-443a-93bb-31e585ece92e · outbound

This paper cites Depth any- thing v2.Advances in Neural Information Processing Sys- tems, 37:21875–21911.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Depth any- thing v2.Advances in Neural Information Processing Sys- tems, 37:21875–21911

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.530718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:6fcf8708af5471f8d1c06c2647b42e7a89977fe27f9218f375098b87ed2caba9

Observation ef8157ea-0388-4423-85a5-8ef76564657f · outbound

This paper cites Sg-nav: Online 3d scene graph prompting for llm-based zero-shot object navigation.Advances in neural information processing systems, 37:5285–5307.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Sg-nav: Online 3d scene graph prompting for llm-based zero-shot object navigation.Advances in neural information processing systems, 37:5285–5307

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.511280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:cc3113564c9f8adb891df8abb93e416c6ca80dcd5290ca24f09a2e6190d72bea

Observation 0b5f5794-ef57-41a2-b741-58c4e0999c52 · outbound

This paper cites Vlfm: Vision-language frontier maps for zero-shot semantic navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Vlfm: Vision-language frontier maps for zero-shot semantic navigation

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.526784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:cd0f884820e3cdebb0c4faba659f81ea2f27838c70355987f09a7f4eb48850a2

Observation 8fe555f7-f895-4f98-89e1-49c950e53140 · outbound

This paper cites Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.541065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:230916a1810f7f55d80760911a3013d248882e2ab36e6b91f079b0059b00b272

Observation 63d7ba44-1569-45c3-baed-59e4fe5ee8ad · outbound

This paper cites Poliformer: Scaling on-policy rl with transformers results in masterful navigators.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Poliformer: Scaling on-policy rl with transformers results in masterful navigators

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.536201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:680d0467ec0104e523e4023b674fb9b7ada9d70f0dfa6fc14a2e3b413e767605

Observation bcb3f5e5-928e-4d3d-8c8d-81e7a74e2fea · outbound

This paper cites Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-16T19:51:36.748157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:fc05509a7284fe3e4a81bcccd68e40d6e04d16ff89f7317f866681dc1f108c19

Observation 2404bc3e-ceb6-4d37-b70e-d96e466a8f28 · outbound

This paper cites NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-18T04:55:20.726672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:2e03dc350bd7286c31bde1f916672b7ebccba3664bfa5d98d1fd2b8314f7b09f

Observation 72f5a89d-5c09-41dd-a10d-bdac202c1b01 · outbound

This paper cites AdaptThink: Reasoning Models Can Learn When to Think.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation AdaptThink: Reasoning Models Can Learn When to Think

Reference 46

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T07:41:01.516836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:9e58c825eb2d6c7bcb12ce07f786831fd2877022e341cc3587ecefdd28d7e0c2

Observation 759b36c4-af32-40cc-b7ee-17dc53b7961c · outbound

This paper cites MapNav: A novel memory representation via annotated semantic maps for VLM-based vision-and-language navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation MapNav: A novel memory representation via annotated semantic maps for VLM-based vision-and-language navigation

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T12:24:36.487185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:d646bd6a5b30df258310f8e6ae2ddeb29b650950f3dad60bbfdcf75e644b2c2d

Observation 2473f15f-604a-4723-bd8b-547e8c3874c5 · outbound

This paper cites Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.414444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:9cb0b0f53240ad3a856f3c538fd55ce3fb3043277c7a84224221d47cc44f273f

Observation 78513c94-4e7b-4b0a-92d5-91f0869b26c4 · outbound

This paper cites ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion

Reference 49

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.457206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:07755bb7abbbf5730b7394dcec5f2bbd9db2d8093f9ded25f95a6a595a827267

Observation 60659adb-a868-41ec-9f4a-81fc05978633 · outbound

This paper cites TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.438885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T17:01:13.350219Z digest=sha256:f54c12c4079a4c9290a7f6e2d61e4a7451768d81790559b2841d135173284030

Pith citing papers

No inbound Pith citation observations are available.