In particular, LLM-based AI agents have demonstrated strong coding capabilities, while harness engineering has further enhanced their ability to interact with the external world, execute actions, and ...
In inference optimization, reward hacking happens when an agent improves its score by exploiting the evaluation without delivering the improvement we actually wanted. This can happen at the kernel ...
GPT-6 Astra edited Qwen’s weights and raised MATH-500 from 7.9% to 48.1% in author-run tests. How weight-space programming works—and its limits.
MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
Tsinghua’s HarnessPro cuts AI coding agent costs 26% while boosting accuracy without model retraining. Factory Droid 1.0 ...
Anthropic sandbox-runtime (srt) is the open-source, OS-level sandbox behind Claude Code. It restricts file and network access ...
OpenHands local setup in 12 steps: run Agent Canvas with Ollama and a local Qwen model in sandboxed Docker, plus a preflight ...
AI can write code that runs. CS coursework tests whether you understand it. Here's where AI code fails and how to check it ...
Startup Recursive has released Flint, a free, laptop-sized coding model built largely by its own AI research system, as an early test of AI that improves itself.
When I asked an AI what it finds beautiful, it returned four lines of Python code.When you create a piece of work, you want ...
A new research paper posted to arXiv on September 14, 2026 is the clearest public evidence yet that Google DeepMind is actively working on systems that improve their own problem-solving strategies ...
Recursive Language Models (RLMs) let a root LM work through contexts far bigger than its window. The context lives in a REPL variable, and the root writes code over it and calls sub-models on pieces ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results