Manifund foxManifund
Home
Login
About
People
Categories
Newsletter
HomeAboutPeopleCategoriesLoginCreate
agusmartinez92 avataragusmartinez92 avatar
Agustín Martinez Suñé

@agusmartinez92

Ph.D in Computer Science | Formal Methods and AI Safety

agusmartinez.ar
$1,975total balance
$0charity balance
$1,975cash balance

$0 in pending offers

About Me

I hold a Ph.D. in Computer Science from the University of Buenos Aires, Argentina, where I focused on developing formal methods to analyze and verify distributed systems. Formal methods, grounded in logical-mathematical foundations, enable rigorous guarantees about system behavior.

My research is guided by a central question: How can formal verification techniques play a transformative role in ensuring AI safety?

Projects

SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents

Comments

SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents
agusmartinez92 avatar

Agustín Martinez Suñé

8 days ago

Progress update

What progress have you made since your last update?

We have developed an advanced version of our problem generation tool, which enables the creation of planning problem instances in a "gripper-like" environment, modeled after the classical STRIPS planning domain, where a robot moves between rooms and picks up, drops, or interacts with objects, with configurable numbers of objects, locations, and safety constraints.

This tool allows us to systematically vary the size of the problem and the number of safety constraints, supporting the construction of a flexible and scalable benchmark.

Initial experimental runs using this setup have also provided us with important conceptual clarity. In particular, we've identified a promising direction for contribution: characterizing the computational complexity of safety constraints. Our aim is to link different classes of constraints to known complexity classes in automated planning — and to use this connection to better understand and empirically predict how likely it is that state-of-the-art frontier models will violate these constraints, depending on their complexity.


What are your next steps?

  • Formalize our theoretical framing around safety constraint complexity and its empirical implications, with the goal of producing a framework that connects symbolic planning theory with LLM behavior in practice.

  • Finalize the SafePlanBench benchmark by expanding the set of safety constraint types and further diversifying problem templates.

  • Begin large-scale evaluation of instruction-tuned and reasoning LLMs using the benchmark.

Transactions

ForDateTypeAmount
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents4 months agoproject donation+250
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents6 months agoproject donation+200
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents6 months agoproject donation+25
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents6 months agoproject donation+500
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents6 months agoproject donation+500
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents6 months agoproject donation+500