Alibaba-Quark / SSP
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
Why this job: works in the areas we cover, but does not say which job it does
What it does
Built upon veRL and Search-R1, SSP extends the traditional self-play paradigm by incorporating tool-augmented reasoning capabilities. Both the proposer (generating challenging problems) and the solver (answering questions) can leverage search engines to access external knowledge during their multi-turn reasoning process.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 106
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 92% closed
- 1 still open
- Pull requests
- 1 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 100%
Topics
- agent
- alibaba
- deep-research
- llm
- reinforcement-learning
- self-play
Project record
- JobOther AI tools
- StatusListed
- Commits10
- Forks9
- Watching4
- Stars in 28 days0
- CreatedOct 21, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026