TIGER-AI-Lab / RewardHarness
Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.
Why this job: topics: evaluation, llm-evaluation, benchmark
What it does
Code release for *RewardHarness: Self-Evolving Agentic Post-Training*, accepted at the Conference on Language Modeling (COLM 2026). Project page: rewardharness.com.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 105
- +4 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.4.1
- Released 2 months ago
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 0% closed
- 4 still open
- Pull requests
- 0 merged
- 3 waiting
- Releases
- 11
- 11 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| modelscope / evalscope | 3,674 | today | Apache-2.0 | No downloads |
| strands-agents / evals | 252 | yesterday | Apache-2.0 | No downloads |
| Prism-Shadow / GDPevo | 121 | 12 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- Shell 7%
- Makefile 1%
Topics
- agentic
- ai-agents
- benchmark
- evaluation
- gemini
- image-editing
- llm-evaluation
- llm-judge
- preference-learning
- qwen-vl
- reward-model
- reward-modeling
Project record
- JobEvals and observability
- StatusListed
- Commits145
- Forks10
- Watching1
- Stars in 28 days+28
- CreatedMay 14, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026