Research desk
An annotated reading list. Every entry is credited to its original authors, with a note on what it changes once the idea meets a real system.
5 entries
A benchmark built from real issue reports and pull requests across popular Python repositories. A model is handed a codebase and a GitHub issue and has to produce a patch that makes the repository test suite pass, which is a far harder target than generating plausible-looking code.
Generalises chain-of-thought into a search tree. The model proposes multiple partial solutions, evaluates them against each other, and can back out of a branch that is not working, rather than committing to one linear line of reasoning.
Agents that keep a natural-language memory stream, reflect over it to form higher-level conclusions, and plan their day from those conclusions. The paper studies what emerges when twenty-five such agents share a small sandbox world.
Instead of updating weights, the agent writes down what went wrong after a failed attempt and carries that reflection into the next attempt. The reflection is stored in natural language and used as additional context, so no gradient step is required.
A model decides for itself when to call an external API, inserts the calls into its own training data, and keeps only the ones that actually reduce its prediction loss. No hand-written tool demonstrations are needed.
The architectures and pre-training results everything else stands on.
3 entries
Grounding a model in documents you actually own.
4 entries
Getting a model to show its work, and checking the work.
5 entries
Models that call tools, hold state, and finish multi-step jobs.
6 entries
Changing what a model does without retraining all of it.
3 entries
Steering outputs toward what a person would accept.
3 entries
How you know it works before a customer finds out it does not.
5 entries