Search papers, labs, and topics across Lattice.
17 papers from Amazon Science on Code Generation & Program Synthesis
Thoughtful feature curation reveals that structural code complexity is a far stronger predictor of deployment risk than traditional change volume metrics.
AutoRestTest outperformed all competitors in the SBFT 2026 Tool Competition, revealing significant advancements in automated REST API testing.
Translating C interpreters to safe Rust can be done with minimal human intervention while completely eliminating memory vulnerabilities.
A robust multi-agent scaffold can unlock latent capabilities in fixed models, enabling a remarkable 67.4% issue resolution rate on SWE-bench Pro鈥攐utpacing the previous best by over 8 percentage points.
Axon can automatically synthesize high-performance tensor programs, drastically simplifying the optimization process for AI accelerators.
Graphical PLC programs can now be verified accurately in under 70ms, eliminating previous vacuous results and enhancing reliability in industrial automation.
All tested coding agents fail within 5-6 turns, but providing feedback can boost their performance by up to 12x, revealing critical insights into agent design.
The largest-ever verification campaign for Rust's standard library reveals significant vulnerabilities in unsafe code, underscoring the need for robust static verification methods.
LLMs can resolve merge conflicts nearly as well as Google's best, but still fail in over 40% of cases, revealing a surprising bottleneck in automating software development.
ESBMC's journey from a research prototype to an autonomous verification kernel integrated with LLMs and deployed industrially at Lockheed Martin signals a paradigm shift towards AI-driven formal verification.
LLMs can now automatically slim down and future-proof mathematical proofs, achieving 70% compression and 60% faster compilation by strategically rewriting them.
Turns out, the best template for documenting architectural decisions depends on whether you value conciseness (Nygard) or structural detail (MADR).
LLMs can now autonomously translate entire C projects to Rust with near-perfect accuracy, thanks to a novel agentic framework that dynamically navigates dependencies and iteratively verifies translations.
Forget wrestling with language-specific tooling: ReCodeAgent autonomously translates and validates entire code repositories across diverse languages with a 60% boost in test pass rates.
LLMs can boost code performance by 25%, but only when working *with* compilers in a carefully orchestrated multi-agent system.
LLMs can automatically generate web vulnerability detection rules with surprisingly high accuracy, but only with careful validation and human oversight to mitigate overconfidence.
Open-source LLMs can now autonomously optimize AI accelerator kernels, matching the performance of proprietary models at a fraction of the cost.
