verifiers 0.1.15.dev169__tar.gz → 0.1.15.dev171__tar.gz

{verifiers-0.1.15.dev169 → verifiers-0.1.15.dev171}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: verifiers
-Version: 0.1.15.dev169
+Version: 0.1.15.dev171
 Summary: Verifiers: Environments for LLM Reinforcement Learning
 Project-URL: Homepage, https://github.com/primeintellect-ai/verifiers
 Project-URL: Documentation, https://github.com/primeintellect-ai/verifiers

{verifiers-0.1.15.dev169 → verifiers-0.1.15.dev171}/verifiers/envs/experimental/composable/tasksets/search/README.md

@@ -8,21 +8,25 @@ The search family is intentionally backend-oriented, mirroring the SWE taskset p
 
 | Backend | Source | Default dataset | Status |
 |---|---|---|---|
+| `openseeker` | [PolarSeeker/OpenSeeker](https://github.com/PolarSeeker/OpenSeeker) | [`PolarSeeker/OpenSeeker-v1-Data`](https://huggingface.co/datasets/PolarSeeker/OpenSeeker-v1-Data) | Binary semantic answer judge |
 | `quest` | [OSU-NLP-Group/QUEST](https://github.com/OSU-NLP-Group/QUEST) | [`osunlp/QUEST-RL-Data`](https://huggingface.co/datasets/osunlp/QUEST-RL-Data) | Objective tasks supported |
+| `redsearcher` | [RedSearchAgent/REDSearcher](https://github.com/RedSearchAgent/REDSearcher) | [`Zchu/REDSearcher_RL_1K`](https://huggingface.co/datasets/Zchu/REDSearcher_RL_1K) | Text RL query set supported |
 
 ## Usage
 
 ```python
 from verifiers.envs.experimental.composable.tasksets.search import make_search_taskset
 
+taskset = make_search_taskset(backend="openseeker")
 taskset = make_search_taskset(backend="quest", category="objective")
+redsearcher = make_search_taskset(backend="redsearcher", difficulty="easy")
 ```
 
 `make_search_taskset()` dispatches by backend name. Unknown backends raise `ValueError` with the available backend list.
 
 ## Output Contract
 
-Search tasksets should define their own output contract. The initial `quest` backend expects the agent to write one final researched response to `/task/answer.txt`, including supporting URLs/citations when available. Scratch reasoning, tool traces, and logs should not be written as the final answer.
+Search tasksets should define their own output contract. The `quest`, `openseeker`, and `redsearcher` backends expect the agent to write one final researched response to `/task/answer.txt`, including supporting URLs/citations when available. Scratch reasoning, tool traces, and logs should not be written as the final answer.
 
 ## Error Handling
 

verifiers-0.1.15.dev171/verifiers/envs/experimental/composable/tasksets/search/__init__.py

@@ -0,0 +1,15 @@
+"""Composable search/research tasksets."""
+
+from .search_tasksets import (
+    make_openseeker_taskset,
+    make_quest_taskset,
+    make_redsearcher_taskset,
+    make_search_taskset,
+)
+
+__all__ = [
+    "make_openseeker_taskset",
+    "make_quest_taskset",
+    "make_redsearcher_taskset",
+    "make_search_taskset",
+]

verifiers-0.1.15.dev171/verifiers/envs/experimental/composable/tasksets/search/openseeker/README.md

@@ -0,0 +1,33 @@
+# OpenSeeker Search Taskset
+
+Composable search taskset for [`PolarSeeker/OpenSeeker-v1-Data`](https://huggingface.co/datasets/PolarSeeker/OpenSeeker-v1-Data), the OpenSeeker v1 release associated with arXiv `2603.15594`.
+
+OpenSeeker v1 data contains synthesized deep-search QA pairs plus trajectories generated with `search` and `visit` tools. The public OpenSeeker evaluator scores only the final answer: it sends the question, gold answer, and model response to an LLM judge and expects `A` for correct or `B` for incorrect. This backend preserves that binary semantic answer-judge contract.
+
+## Usage
+
+```python
+from verifiers.envs.experimental.composable.tasksets.search import make_search_taskset
+
+taskset = make_search_taskset(backend="openseeker")
+```
+
+## Arguments
+
+| Argument | Default | Description |
+|---|---:|---|
+| `dataset_name` | `PolarSeeker/OpenSeeker-v1-Data` | Hugging Face dataset name. |
+| `split` | `train` | Dataset split. |
+| `trajectory_correctness` | `Correct` | Keep rows with this trajectory label. Use `None` or `all` for all rows. |
+| `min_tool_calls` | `None` | Optional lower bound for `number of tool calls`. |
+| `max_tool_calls` | `None` | Optional upper bound for `number of tool calls`. |
+| `include_trajectory` | `False` | Include the large source trajectory in task metadata. |
+| `answer_file` | `/task/answer.txt` | Final answer path in the sandbox. |
+| `judge_model` | `openai/gpt-5.4-mini` | OpenAI-compatible model used for binary answer judging. |
+| `judge_base_url` | `https://api.pinference.ai/api/v1` | Judge API base URL. |
+| `judge_api_key_var` | `PRIME_API_KEY` | Env var containing the judge API key. |
+| `judge_sampling_args` | `None` | Extra sampling args for judge calls. |
+
+## Output Contract
+
+Agents should write one final answer to `/task/answer.txt`. The answer should directly satisfy the question and may include supporting URLs/citations. The judge ignores citation verification and evaluates whether the final response semantically contains the gold answer without contradictions.

verifiers-0.1.15.dev171/verifiers/envs/experimental/composable/tasksets/search/openseeker/__init__.py

@@ -0,0 +1,5 @@
+"""OpenSeeker search taskset."""
+
+from .taskset import OpenSeekerRubric, OpenSeekerTaskSet
+
+__all__ = ["OpenSeekerRubric", "OpenSeekerTaskSet"]