Skip to content
AI News HubLIVE
Original source2 min read

Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response

Summary

This paper identifies a class of assistance games where pragmatic-pedagogic reasoning resolves goal uncertainty in a single step, enabling tractable exact solutions, and shows that inverse optimal control has an inference ceiling that this reasoning overcomes.

SourcearXiv RoboticsAuthor: Elle Lazarski, Jaime Fern\'andez Fisac
Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 29 Jul 2026]

Title:Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response

View a PDF of the paper titled Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response, by Elle Lazarski and Jaime Fern\'andez Fisac

View PDF

Abstract:Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observation and interaction in order to assist effectively. In general, computing optimal assistance game strategies online is intractable, since exact solutions require planning in a POMDP. We identify a class of assistance games in which pragmatic-pedagogic reasoning resolves goal uncertainty in a single time step, rendering the full-horizon game exactly solvable by a tractable best-response procedure. Within this class, we show that mainstream inverse optimal control exhibits an inference ceiling that hinders alignment, while pragmatic-pedagogic reasoning overcomes this barrier by immediately disambiguating goals through actions that look equivalent under task execution alone. Finally, we validate our theoretical results and proposed method on a simple collaborative block-building example.

Comments: World Symposium on the Algorithmic Foundations of Robotics (WAFR) 2026

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2607.27508 [cs.RO]

(or arXiv:2607.27508v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.27508

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Elle Lazarski [view email] [v1] Wed, 29 Jul 2026 22:49:28 UTC (902 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response, by Elle Lazarski and Jaime Fern\'andez Fisac

View PDF

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Assistance games model human-robot collaboration under asymmetric information, where the robot must infer the human's goal.
  • The authors find a class of games where pragmatic-pedagogic reasoning disambiguates goals in one time step, making the full-horizon game exactly solvable via a tractable best-response procedure.
  • Mainstream inverse optimal control exhibits an inference ceiling that hinders alignment, while pragmatic-pedagogic reasoning overcomes it by using actions that are equivalent for task execution but informative for teaching.
  • The theoretical results and method are validated on a collaborative block-building example.

Highlights and analysis are generated automatically and may contain errors. Check the original source.