A new way to help agents remember work for future tasks
The CoReMem framework helps agents decide what information is worth saving to reduce effort in upcoming tasks.
The CoReMem framework helps agents decide what information is worth saving to reduce effort in upcoming tasks.
A new recommender selects between two steady-state detection methods for benchmark time series.
Arknife uses a constraint-based layout algebra to handle instruction requirements across different hardware targets.
Researchers studied how public and private groups share data to improve last-mile logistics in Sweden.
The QAOA-TCS approach shows stable performance even when facing high levels of quantum noise.
Current predictors mostly identify issue difficulty and model ability instead of the run itself.
Researchers created Reaper to find related errors by studying past bug fixes.
GraphWeave uses an integrated testing approach to uncover previously unknown defects in the NeuG database.
SymFC uses configurable semantics to help verify properties in Haskell programs.
Researchers evaluated the verification pipelines of SD-JWT VC, W3C Verifiable Credentials Data Model 2.0, and mdoc.
The Artifact Model for Regulatory Requirements Engineering uses templates to coordinate different viewpoints.
A study examines how file text, dependencies, and folders help map code to architecture.
A new framework uses algorithmic structure to check large quantum circuits.
Researchers found that information from a compiler front end can represent and change the hidden states of code models.
Researchers suggest a semi-automated method to link complex C or C++ code to Python for epidemic modeling.
Researchers extended weighted programming to include user-defined additive rewards and countable nondeterminism.
Researchers analyzed how different Python linters compare in speed, rules, and configuration.
Structured tools can double accuracy for certain small model sizes.
The CC4Q Workbench automates the process of extracting and classifying explanations found in quantum software repositories.
The OSTEON discipline uses governed knowledge repositories and mechanical checks to manage software built by agents.
ATLAS uses multiple agents to reconstruct LLVM intermediate representation from optimized binaries.
MEDiml connects feature extraction and predictive modeling through graphical and programmatic interfaces.
This framework connects images and reports to predict building recovery and downtime.
The Quantum Broker framework distributes quantum circuits across multiple processors to meet specific user needs.