Models that call tools, hold state, and finish multi-step jobs.
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.
Interleaves verbal reasoning traces with tool actions, so the model thinks about what to do next, does it, then reasons about what came back. The reasoning trace also becomes an auditable record of why the agent took each step.