No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from InternScience/Sage-A1.5-FP8
All models by InternScience →[!Note] This repository contains model weights and configuration files for Sage-A1.5 in the Hugging Face Transformers format.
These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
Sage‑A1.5 is a 35B Mixture‑of‑Experts agentic model based on Qwen3.6 and Agents-A1 from Shanghai AI Laboratory, built to advance long-horizon scientific problem solving through adaptive capability composition. Building upon Agents‑A1, Sage‑A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution, highlighting three key capabilities: Agentic Orchestration, Verification, and Open Scientific Discovery.
First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing Sage‑A1.5 to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We hope Sage‑A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.
We welcome developers and enterprises to integrate and try Sage-A1.5 and share their feedback.
We evaluate Sage-A1.5 in real-world agentic and research-oriented workflows across six directions — long-horizon search, engineering tasks, instruction following, scientific research, general agentic tasks, and scientific agentic tasks. Despite operating in the ~35B model class, Sage-A1.5 delivers highly competitive performance against frontier-scale systems such as Kimi-K3, GLM-5.3, and GPT-5.6-sol. It achieves overall SOTA on XBench-DS-2510 (92.0), IFBench (81.6), PinchBench (90.0), FrontierScience-Olympiad (81.0), FrontierScience-Research (48.3), CMT (80.0), and OmniDocBench (91.5), and reaches 95.1 on GAIA — higher than every larger-scale model we compare against. Among comparable ~35B models it ranks first on a broad range of tasks, including BrowseComp (81.7), SWE-bench Pro (61.2), MLE-Lite (65.2), SciCode (44.3, tied with Agents-A1), AA-LCR (81.0), HLE w/ tools (55.1), VitaBench (45.4), and ChemCOTBench (66.5). Compared with A1, it improves substantially on engineering and agentic workloads (SWE-bench Pro +17.6, SWE-bench Multilingual +14.0, PinchBench +13.1, MLE-Lite +21.3). These results show that Sage-A1.5 combines strong long-horizon search ability, robust scientific reasoning, and reliable instruction following, establishing it as a highly capable and efficient agentic model that narrows the gap with much larger frontier models.
🥇 Overall SOTA 🟢 Best Among Comparable Models (~35B)
[!Note] SWE-Bench Series: We use the mini-SWE-agent harness with a temperature of 1.0, top-p of 0.95, a 200K-token context window, and automatic context compaction enabled. All evaluations are conducted in a fully offline environment without internet access.
GLM-5.3 on OmniDocBench: GLM-5.3 is a text-only (unimodal) model without multimodal input support, so its results on OmniDocBench, a multimodal benchmark, are not reported.
SGLang is a fast serving framework for large language models and vision language models.
Install SGLang with uv:
See its documentation for more details.
The following commands create API endpoints at http://localhost:8000/v1:
Standard Version:
Multi-Token Prediction (MTP):
Sage-A1.5 natively supports a 256K context window. To extend it to 512K, serve the model with
YaRN (factor: 2.0) enabled by overriding the RoPE parameters:
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.
Install vLLM from the main branch via uv:
See its documentation for more details.
The following commands create API endpoints at http://localhost:8000/v1:
Standard Version (1 GPUs, 262K context):
Text-Only (skips vision encoder to free KV cache memory):
Multi-Token Prediction (MTP):
Sage-A1.5 natively supports a 256K context window. To extend it to 512K, serve the model with
YaRN (factor: 2.0) enabled via --hf-overrides (vLLM no longer supports the old --rope-scaling
flag):
Sage-A1.5 ships two opt-in modes that build on the standard serving setup above. Both are off by default: Agentic Orchestration Mode is turned on by registering a tool, Verification Mode by a chat-template flag.
Agentic Orchestration Mode (see Highlights) lets the model fan out independent sub-questions to
sub-agents that run in parallel, each with its own context window and its own tool access. It is
enabled by exposing a spawn_subagent tool to the model: the model calls it whenever a task
decomposes into independent investigations, and your harness runs each sub-task and returns the
structured results.
Sub-agents are not restricted to any fixed tool set — they can be given whatever tools your
deployment registers (search, page reading, code execution, retrieval, internal APIs, …). By default
they inherit the main agent's tools; set subagent_tools if you want them to have a different, for
instance narrower, set.
Register the following tool schema alongside your other tools:
Because a sub-agent cannot see the main conversation, every task must be self-contained — task,
context, and expected_output are all required. Each sub-agent returns one compact JSON object
{answer, status, evidence, unresolved_issues}, and the batch is handed back to the main model in
input order.
Notes:
spawn_subagent calls.expected_output acts as a format constraint on the sub-agent's answer (e.g. 'a year YYYY',
'a person name'), which keeps results short and easy to merge."UNKNOWN" with a status of unknown or
insufficient_evidence rather than guessing — check status before using an answer.max_tasks_per_spawn, default 5; subagent_max_turns, default 20). Oversized batches are
rejected with an error message instead of being truncated.description above names google_search and read_page because that is the
reference setup. If you give sub-agents a different tool set, update that sentence to match —
it is what tells the main model what its sub-agents can actually do.Verification Mode (see Highlights) is opt-in and off by default. Enable it per request by
passing verification through chat_template_kwargs; the chat template then appends the verification
protocol trigger to the end of your system message.
OpenAI Python client (via extra_body):
curl:
Notes:
verification: true and no system message (or a whitespace-only one) is
rejected with HTTP 400.{"verification": true}, not {"verification": "true"}.chat_template_kwargs is equivalent to {"verification": false}, which renders the prompt
unchanged.tools.reasoning_content in addition to content.For the best generation quality, we recommend the following sampling parameters:
temperature: 1.0top_p: 0.95top_k: 20min_p: 0.0presence_penalty: 1.5repetition_penalty: 1.0To provide the community with a unified agent evaluation codebase for fair comparison, we have also open-sourced an evaluation framework for assessing agentic models across core capabilities, including tool use and multi-step reasoning. The evaluation code is included in the Sage-A1/evaluation of this repository.
We use this framework to evaluate the released model under a standardized and reproducible setting. Specifically, the model is tested on a set of agent-oriented tasks that require it to understand user goals, decompose complex instructions, interact with tools or environments when necessary, and produce final results. The evaluation results reported in Model Card are generated using the open-source framework above, so that users can reproduce the experiments, compare other models under the same protocol, and further extend the benchmark for new agent scenarios. (Note that: To ensure a fair comparison, we report the benchmark results from their original technical reports. If a model does not report the corresponding benchmark results, we evaluate it using the same evaluation protocol as our model.)
For detailed evaluation scripts, task definitions, metrics, and reproduction instructions, please refer to the evaluation codebase.
If you find our work helpful, feel free to give us a cite.
uv venv --python 3.12 --seed --managed-pythonsource .venv/bin/activate
uv pip install sglangpython -m sglang.launch_server \ --model-path InternScience/Sage-A1.5 \ --port 8000 \ --mem-fraction-static 0.8 \ --context-length 262144 \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coderpython -m sglang.launch_server \ --model-path InternScience/Sage-A1.5 \ --port 8000 \ --mem-fraction-static 0.8 \ --context-length 262144 \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder \ --speculative-algorithm EAGLE \ --speculative-num-steps 3 \ --speculative-eagle-topk 1 \ --speculative-num-draft-tokens 4SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 \python -m sglang.launch_server \ --model-path InternScience/Sage-A1.5 \ --port 8000 \ --context-length 524288 \ --json-model-override-args '{ "text_config": { "rope_parameters": { "mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 2.0, "original_max_position_embeddings": 262144 } } }' \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder \ --mem-fraction-static 0.88uv venv --python 3.12 --seed --managed-pythonsource .venv/bin/activate
uv pip install vllm --torch-backend=autovllm serve InternScience/Sage-A1.5 \ --port 8000 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser qwen3_codervllm serve InternScience/Sage-A1.5 \ --port 8000 \ --tensor-parallel-size 1 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --language-model-onlyvllm serve InternScience/Sage-A1.5 \ --port 8000 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser qwen3_coder \ --speculative-config '{"method":"mtp","num_speculative_tokens":3,"moe_backend":"triton"}'VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \vllm serve InternScience/Sage-A1.5 \ --port 8000 \ --max-model-len 524288 \ --hf-overrides '{ "text_config": { "rope_parameters": { "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 2.0, "original_max_position_embeddings": 262144, "mrope_interleaved": true, "mrope_section": [11, 11, 10] } } }' \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser qwen3_coderSPAWN_SUBAGENT_SCHEMA = { "type": "function", "function": { "name": "spawn_subagent", "description": ( "Dispatch one or more sub-agents IN PARALLEL to investigate independent " "sub-questions. Each sub-agent has access to google_search and read_page " "but CANNOT see your conversation. You MUST give each sub-agent everything " "it needs via the `task`, `context`, and `expected_output` fields. Sub-agents " "return structured JSON: {answer, status, evidence, unresolved_issues}." ), "parameters": { "type": "object", "properties": { "tasks": { "type": "array", "minItems": 1, "description": "List of independent sub-tasks to dispatch in parallel.", "items": { "type": "object", "properties": { "task": { "type": "string", "description": "Self-contained sub-question. The sub-agent has no other context.", }, "context": { "type": "string", "description": "Background facts and constraints the sub-agent needs.", }, "expected_output": { "type": "string", "description": "Form of the desired answer (e.g. 'a year YYYY', 'a person name').", }, }, "required": ["task", "context", "expected_output"], }, }, }, "required": ["tasks"], }, },}from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create( model="InternScience/Sage-A1.5-FP8", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Find the population of Beijing and cross-check it."}, ], tools=TOOLS, extra_body={"chat_template_kwargs": {"verification": True}},)
message = response.choices[0].messageprint(message.reasoning_content) # self-review happens inside the chain of thoughtprint(message.content)curl http://localhost:8000/v1/chat/completions \ -H 'Content-Type: application/json' \ -d '{ "model": "InternScience/Sage-A1.5-FP8", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Find the population of Shanghai and cross-check it."} ], "chat_template_kwargs": {"verification": true} }'@misc{lou2026sagea15longhorizonexecutionscientific, title={Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition}, author={Sage-A1.5 Team}, year={2026}, eprint={2610.28578}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2610.28578}, }