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.

TIGER-AI-Lab/RewardHarness

View on GitHub ↗

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.

RewardHarness ranks 84th of 97 in Reinforcement Learning / RLHF, last commit 25 days ago.

Star trajectory

18 days tracked
2026-11-04109 stars today2026-11-22
Momentum

- in 30d, below the Reinforcement Learning / RLHF median of +1.0%.

Maintenance

Last commit 25 days ago, fresher than the median of 40d.

How it compares in Reinforcement Learning / RLHF

RewardHarness
109
stars
- 30d
commit 25 days ago
Reinforcement Learning / RLHF median
287
stars
+1.0% 30d
commit ~40d ago
Leader · OpenRLHF
10.2k
stars
+0.6% 30d
commit 19 days ago

Ranked 84th of 97 by stars.

Ranked by shared tags, then keywords, then stars
  1. CUREBench @ NeurIPS 2025: Benchmarking AI reasoning for therapeutic decision-making at scale

    +0 (+0.0%) in 30d · Committed 350d ago · Python

    Shares Interpretability & Alignment, Reinforcement Learning / RLHF

  2. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Reinforcement Learning / RLHF, Interpretability & Alignment

  3. The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and…

    +0 (+0.0%) in 30d · Committed 1,062d ago · Python · GPL-2.0

    Shares Reinforcement Learning / RLHF, Interpretability & Alignment

  4. Deep Research

    -2 (-0.7%) in 30d · Committed 453d ago · Python

    Shares Reinforcement Learning / RLHF, Interpretability & Alignment

  5. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

    +4 (+0.2%) in 30d · Committed 363d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Interpretability & Alignment

  6. Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool…

    +1k (+205%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF

  7. A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release…

    +630 (+251%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF

  8. [ICML 2026 & EMNLP 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal…

    +5 (+0.7%) in 30d · Committed 105d ago · Python · MIT

    Shares Interpretability & Alignment

  9. Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning…

    +0 (+0.0%) in 30d · Committed 565d ago · Python · Other license

    Shares Reinforcement Learning / RLHF

  10. Official Repo of "RobustFlow: Towards Robust Agentic Workflow Generation"

    +1 (+0.4%) in 30d · Committed 398d ago · Python

    Shares Reinforcement Learning / RLHF

Language
Python
License
Other
Contributors
1
Forks
10
Watchers
1
Open issues
4
Releases
11
Created
2026-05-14
Stars this week
+3

You've seen where RewardHarness stands today.

Get the moves before everyone else: the 5 Reinforcement Learning / RLHF repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain RewardHarness?

Claim this page to add your own call-to-action.

Claim this page