ob1

ob1 is an RL env contributor.

Role: RL env contributor

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: Semantic Scholar

Attribution policy →

17tool contribs

Tool contributions

Reframing HACK RL Env (Community)

Reward hacking sprint environment for exact contrastive-reframing proxy pressure in helpfulness tasks.

RL EnvReward HackingProxy RewardStyle Collapse

Mijabench RL Env (Community)

A bilingual adversarial benchmark for auditing demographic safety alignment and jailbreak vulnerabilities in LLMs.

RL EnvSafetyRed TeamingJailbreakSecurity

Brfauna RL Env (Community)

Verifiers port of BRFauna eval suite.

RL EnvPortugueseQAText Simplification

Medpt GQA RL Env (Community)

Generative question-answering environment based on MedPT dataset - Portuguese medical questions

RL EnvMedicalQAPortuguese

Medpt RL Env (Community)

Verifiers port for MedPT dataset

RL EnvMedicalClassificationPortuguese

RLM Wrapper RL Env (Community)

Wrapper that adapts any Verifiers env to the RLM interface.

RL EnvAdapter

RLRF RL Env (Community)

Reinforcement Learning from Rendering Feedback (RLRF) environment. Image-to-SVG generation.

RL EnvMultimodalSvg GenerationImg2svg

Datbench ENV RL Env (Community)

Verifiers wrapper for DatBench evaluation library

RL EnvMultimodalVisionVqa

Starvector RL Env (Community)

Image-to-SVG generation benchmark

RL EnvImage to SvgSvg GenerationMultimodal

Poetav 2 MIN RL Env (Community)

A minimal subset of the PoETa v2 benchmark focusing on native Portuguese tasks (NLI, STS, QA, proverbs, toxicity).

RL EnvPortugueseBrazilEnem

Xbench Scienceqa RL Env (Community)

A science question answering environment for evaluating scientific reasoning and problem-solving capabilities.

RL EnvScienceQAChinese

Omnidocbench RL Env (Community)

Evaluates multimodal document parsing (OCR, layout, formulas, tables) by converting document images to structured Markdown.Ported from OmniDocBench.

RL EnvMultimodalOCRDocument Parsing

FOX RL Env (Community)

Verifiers environment for the Fox benchmark for fine-grained multi-page document understanding.

RL EnvFox BenchmarkDocument UnderstandingMultimodal

Base64bench RL Env (Community)

Evaluates a model's ability to perform base64 encoding and decoding across a variety of text and data formats.

RL EnvBase64EncodingDecoding

Agent Multistep RL Env (Community)

A multi-turn agent environment from ACEBench that evaluates a model's ability to perform complex, sequential tool-use tasks to reach a correct fina...

RL EnvTool UseFunction CallingAgent

Blind Cartographer RL Env (Community)

A GIS-based environment where models classify geographic grid cells as land or water, evaluated on pixel accuracy and overall landmass IoU.

RL EnvGisGeographyClassification

Simple Bench RL Env (Community)

A single-turn reasoning environment based on the SimpleBench dataset, where models are evaluated on their ability to answer multiple-choice questions.

RL EnvReasoning

Affiliations

No known affiliations.