Papers › Behavior Cloned Transformers are Neurosymbolic Reasoners

Behavior Cloned Transformers are Neurosymbolic Reasoners

13 Oct 2022arXiv:2210.07382archive 2025-07-28

Ruoyao Wang, Peter Jansen, Marc-Alexandre Côté, Prithviraj Ammanabrolu

In this work, we explore techniques for augmenting interactive agents with information from symbolic modules, much like humans use tools like calculators and GPS systems to assist with arithmetic and navigation. We test our agent's abilities in text games -- challenging benchmarks for evaluating the multi-step reasoning abilities of game agents in grounded, language-based environments. Our experimental study indicates that injecting the actions from these symbolic modules into the action space of a behavior cloned transformer agent increases performance on four text game benchmarks that test arithmetic, navigation, sorting, and common sense reasoning by an average of 22%, allowing an agent to reach the highest possible performance on unseen games. This action injection technique is easily extended to new agents, environments, and symbolic modules.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cognitiveailab/neurosymbolic officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Common Sense Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GPSTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections