| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | pkg/aflow: make LLM model per-agent rather than per-flow | Dmitry Vyukov | 2026-01-20 | 1 | -0/+1 |
| | | | | | | | Having LLM model per-agent is even more flexible than per-flow. We can have some more complex tasks during patch generation with the most elaborate model, but also some simpler ones with less elaborate models. | ||||
| * | pkg/aflow: add ability to generate several candidate replies for LLM agents | Dmitry Vyukov | 2026-01-19 | 1 | -0/+4 |
| | | | | | | | | | | Add LLMAgent.Candidates parameter. If set to a value N>1, then the agent is invoked N times, and all outputs become slices. The results can be later aggregated by another agent, as shown in the test. | ||||
| * | pkg/aflow/trajectory: add package | Dmitry Vyukov | 2026-01-05 | 1 | -0/+112 |
 |
index : syz | |
| Unnamed repository; edit this file 'description' to name the repository. | root |
| aboutsummaryrefslogtreecommitdiffstats |