Agents-A1 is a 35.11B-parameter mixture-of-experts agentic language model from InternScience, released June 30, 2026 on Hugging Face and ModelScope under Apache 2.0. It targets long-horizon search, engineering tasks, scientific research, instruction following, and tool calling with 256K native context. The technical report is titled "Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent" (arxiv:2606.30616).

How does Agents-A1 compare to Qwen 3.6 35B A3B?

On InternScience's published table, Agents-A1 beats Qwen3.6-35B-A3B on BrowseComp (75.51 vs 67.93), GAIA (96.04 vs 78.64), Seal-0 (56.36 vs 38.74), IFBench (80.61 vs 64.4), and IFEval (94.82 vs 91.3). SciCode is closer — 44.33 vs 35.8, both well below GPT-5.5's 56.1. For local MoE coding quality vs dense trade-offs, see explainx.ai's Qwen 3.6 27B hands-on guide.

Can I run Agents-A1 locally?

Weights are Hugging Face Transformers safetensors — not GGUF for llama.cpp at launch. Serve with vLLM or SGLang on a GPU with enough VRAM for a 35B MoE at 262K context (InternScience documents single-GPU configs with --max-model-len 262144). Consumer laptops should use API hosting or quant ports when community GGUF drops. See the vLLM/SGLang blocks in this post.

Does Agents-A1 support tool calling?

Yes. The model card documents vLLM and SGLang launches with --enable-auto-tool-choice and --tool-call-parser qwen3_coder (vLLM) or --tool-call-parser qwen3_coder (SGLang). Recommended sampling includes temperature 0.85, top_p 0.95, top_k 20, presence_penalty 1.1.

Is Agents-A1 related to Qwen-AgentWorld?

The Hugging Face model card lists architecture tag qwen3_5_moe, and X commenters note lineage overlap with Qwen's agent stack — InternScience does not foreground AgentWorld in the launch copy. Functionally, Agents-A1 is a policy/agent model trained for multi-step tool use; Qwen-AgentWorld is a language world model that simulates environment observations. They address different sides of the agent loop — see explainx.ai's AgentWorld guide for the distinction.

What benchmarks did Agents-A1 claim SOTA on?

Overall SOTA (per model card, June 30 2026): Seal-0 (56.4), HiPhO (46.4), FrontierScience-Olympiad (79.0), FrontierScience-Research (40.0), IFBench (80.6), IFEval (94.8). Best among ~35B-class models on BrowseComp (75.5), XBench-DS-2510 (86.0), GAIA (96.0), SciCode (44.3), HLE with tools (47.6), and MolBench-bind (56.8). Frontier-scale models still lead some rows — e.g. GPT-5.5 on BrowseComp (84.4), Kimi-K2.6 on τ2-Bench (82.2).

Agents-A1 — 35B MoE Agent Model (June 2026) | explainx.ai Blog

explainx.ainewsletter3.4k

workshops ↗

Agents-A1 — 35B MoE Agent Model (June 2026) | explainx.ai Blog | explainx.ai

June 30, 2026 — 4:19 PM: ModelScope announced Agents-A1 on X — a 35B MoE agentic model from InternScience built for long-horizon search, engineering, scientific research, instruction following, and tool calling. Weights landed on Hugging Face the same day under Apache 2.0, with a technical report claiming trillion-parameter-class agent performance without trillion-parameter weights.

The launch sits in a crowded week: LongCat-2.0 from Meituan, ongoing Qwen 3.6 local-dev hype, and Fable 5 still offline. Agents-A1's pitch is different — not raw coding SWE scores alone, but heterogeneous agent horizons: search loops, science tools, instruction evals, and function-calling at 256K context.

TL;DR — what people asked on X

Question	Answer
What is it?	35.11B MoE agent model, `qwen3_5_moe` architecture, 262K server context
License?	Apache 2.0 — enterprise-friendly
On Hugging Face?	Yes — `InternScience/Agents-A1` safetensors
Coding?	SciCode 44.3 — competitive in ~35B class, not frontier (GPT-5.5 56.1)
vs Qwen AgentWorld?	Different job — AgentWorld simulates envs; Agents-A1 is the acting agent. Shared Qwen-family DNA per HF tags; launch copy doesn't cite AgentWorld
256K enough for agents?	Debatable — beats most open models on long-bench rows, but real agent runs accumulate tool I/O fast. Treat context as necessary, not sufficient
How to run?	vLLM or SGLang — not llama.cpp GGUF at ship

What InternScience claims

Paper title: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent (arxiv:2606.30616, dated June 29, 2026).

Two scaling axes:

Long-horizon trajectories — a domain-grounded knowledge-action infrastructure that jointly constructs actions, observations, and verifier outcomes so multi-step agent runs become trainable targets, not one-off demos.
Heterogeneous agent abilities — a three-stage pipeline:
- Full-domain supervised fine-tuning for broad agent behaviors
- Domain teacher models for specialized expertise (search vs science vs engineering)
- Multi-teacher, multi-domain on-policy distillation with heterogeneity-aware optimization

That framing rhymes with Qwen 3.7-Max environment scaling and self-harness agent improvement — the 2026 consensus is that agent quality scales with trajectory diversity, not just parameter count.

InternScience also open-sourced an evaluation framework in the repo (Agents-A1/evaluation) so others can reproduce agent-capability scores under one protocol — a move toward the standardized eval hygiene we cover in the AI benchmarks guide.

Benchmark table — where 35B punches up

Legend from the model card: 🥇 overall SOTA · 🟢 best among ~35B comparables

Long-horizon search

Benchmark	Agents-A1	Qwen3.6-35B-A3B	Kimi-K2.6	GPT-5.5 (xhigh)
BrowseComp	🟢 75.51	67.93	83.2	🥇 84.4
XBench-DS-2510	🟢 86.0	71.0	🥇 90.0	84.0
Seal-0	🥇 56.36	38.74	50.45	42.34
GAIA	🟢 96.04	78.64	80.58	87.38

explainx.ai read: GAIA 96 and BrowseComp 75.5 are the headline numbers for teams building search + tool agents — the same benchmark family LongCat-2.0 cites at 79.9 (different harness/protocol — always compare apples-to-apples).

Scientific research

Benchmark	Agents-A1	Qwen3.6-35B-A3B	DeepSeek-V4-pro
FrontierScience-Olympiad	🥇 79.0	60.3	76.0
FrontierScience-Research	🥇 40.0	2.9	13.3
HiPhO	🥇 46.4	37.7	38.7
HLE w/ tools	🟢 47.6	36.2	48.2

Strongest story: research-agent tasks with tools — relevant for RAG + calculator + literature search stacks, not pure chat.

Instruction following

Benchmark	Agents-A1	Qwen3.6-35B-A3B	GPT-5.5
IFBench	🥇 80.61	64.4	75.9
IFEval	🥇 94.82	91.3	93.35
LongBench-v2	🟢 60.2	57.7	—

If your product fails on multi-constraint prompts (format + content + exclusions), this row matters more than MMLU.

Engineering / coding (the skeptical row)

Benchmark	Agents-A1	Qwen3.6-35B-A3B	Kimi-K2.6	GPT-5.5
SciCode	🟢 44.33	35.8	53.5	🥇 56.1
MLE-Lite	🟢 43.94	34.85	62.12	🥇 72.73

X asked "What about coding?" — fairly. Agents-A1 wins its weight class but Kimi K2.6 and GPT-5.5 lead on SciCode. For repo-scale coding agents, prioritize Kimi K2.7-Code, LongCat-2.0, or dense local Qwen 3.6 27B until independent Terminal-Bench / SWE-bench runs appear.

Architecture and lineage

Field	Value
Parameters	35.11B (MoE)
Format	Safetensors, BF16
Architecture tag	`qwen3_5_moe`
Context	256K native; servers document 262144 max
Modalities	Text + vision encoder (text-only mode skips vision to free KV cache)
License	Apache 2.0

The qwen3_5_moe tag and ModelScope distribution place Agents-A1 in the Alibaba / Qwen ecosystem orbit — alongside Qwen-AgentWorld (35B-A3B world model, June 23) and the China free-models playbook.

AgentWorld vs Agents-A1:

	Qwen-AgentWorld	Agents-A1
Role	Predict environment observations	Execute agent policy (plan, call tools)
Training focus	World-model / simulation RL	Multi-teacher agent distillation
Open weights	35B-A3B MoE	35B MoE

X commenters suggesting "basically Qwen AgentWorld rebranded" oversimplify — but teams evaluating both should read AgentWorld's paper and Agents-A1's distillation story as complementary, not duplicate.

How to run Agents-A1 (vLLM and SGLang)

Weights are Transformers safetensors — use vLLM or SGLang, not llama.cpp until community GGUF quantizers ship.

SGLang — standard server

uv venv --python 3.12 --seed --managed-python
source .venv/bin/activate
uv pip install sglang

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server \
  --model-path InternScience/Agents-A1 \
  --port 8000 \
  --tp-size 1 \
  --mem-fraction-static 0.8 \
  --context-length 262144 \
  --reasoning-parser qwen3

OpenAI-compatible API: http://localhost:8000/v1

SGLang — tool calling

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server \
  --model-path InternScience/Agents-A1 \
  --port 8000 \
  --tp-size 1 \
  --mem-fraction-static 0.8 \
  --context-length 262144 \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder

vLLM — standard server

uv venv --python 3.12 --seed --managed-python
source .venv/bin/activate
uv pip install vllm --torch-backend=auto

VLLM_USE_MODELSCOPE=true vllm serve InternScience/Agents-A1 \
  --port 8000 \
  --tensor-parallel-size 1 \
  --max-model-len 262144 \
  --reasoning-parser qwen3

vLLM — tool calling

VLLM_USE_MODELSCOPE=true vllm serve InternScience/Agents-A1 \
  --port 8000 \
  --tensor-parallel-size 1 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

Text-only (save KV cache)

VLLM_USE_MODELSCOPE=true vllm serve InternScience/Agents-A1 \
  --port 8000 \
  --tensor-parallel-size 1 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --language-model-only

Recommended sampling (from model card)

Parameter	Value
`temperature`	0.85
`top_p`	0.95
`top_k`	20
`min_p`	0.0
`presence_penalty`	1.1
`repetition_penalty`	1.0

Wire to agent harnesses

Point any OpenAI-compatible harness at http://localhost:8000/v1:

OpenCode — opencode.jsonc baseURL
Codex OSS — local provider
Claude Code / OpenClaw — if your stack supports custom OpenAI endpoints

For MCP-heavy loops, run the tool-call parser variant and validate with your real server set — benchmark tool rows don't guarantee clean JSON on your schema.

What X got right (and what to verify)

Reasonable hype

IFEval / IFBench SOTA — instruction-following is a real product surface; numbers are strong.
FrontierScience-Research 40.0 — large jump vs 35B peers (2.9–6.7 range in table).
Open eval code — rare and useful; run it before procurement.

Skepticism to keep

"256K is not enough for agent" — long-horizon agents blow context with tool payloads, retries, and state snapshots. 256K helps; state externalization and compaction still required.
"7 steps before state drift" (Gregor's reply) — real-world agent runs fail on memory coherence, not just benchmark max scores.
Coding — wait for Terminal-Bench 2.0 / SWE-bench reproductions on your harness before replacing Kimi/LongCat/Qwen dense locals.
Vendor tables — when a model doesn't report a benchmark, InternScience says they evaluated under their protocol; cross-check against original vendor papers.

Where Agents-A1 fits in the 2026 open-agent ladder

Coding-first open MoE     →  LongCat-2.0, Kimi K2.7-Code
Local daily driver (dense)  →  Qwen 3.6 27B + llama.cpp
World-model / sim RL        →  Qwen-AgentWorld
Heterogeneous long-horizon  →  Agents-A1  ← this launch
Closed frontier (if allowed)→  GPT-5.5, Fable/Mythos (offline)

During the US export ban on Fable/Mythos, Apache 2.0 agent models that excel at search + science + instructions fill a different niche than GLM-5.2 coding plans — tier workloads like explainx.ai recommends in closed vs open alternatives.

Update — June 29, 2026: Apodex-1.0-mini — another Qwen3.5-35B-A3B agent fine-tune — topped FutureX at 59.17, beating Sonnet 4.6 and GPT-5.5 on future prediction. Agents-A1 targets heterogeneous benchmarks; Apodex targets verification-centric deep research.

Reproduction checklist

Pull weights — huggingface-cli download InternScience/Agents-A1 or ModelScope mirror
Serve with tools — vLLM/SGLang commands above on a GPU box with headroom for 262K KV
Clone eval — Agents-A1/evaluation from the GitHub repo linked on Hugging Face
Run your agent loop — same MCP/search tools you use in production
Compare MoE vs dense — if instruction-following regresses on repo tasks, try Qwen 3.6 27B dense locally
Log horizon length — steps until drift; benchmarks won't show this

Add verification loops from explainx.ai loops when agents drive CI.

Related on explainx.ai

Qwen-AgentWorld — language world model — environment simulation vs agent policy
Qwen 3.6 27B local dev — dense vs MoE — hands-on MoE skepticism
LongCat-2.0 — 1.6T MoE coding agent — same-day launch, coding focus
Kimi K2.7-Code — open coder alternative
Qwen 3.7-Max — long-horizon autonomy — Alibaba agent scaling thesis
Run open-source models in OpenCode — wire local APIs to harnesses
AI benchmarks complete guide — GAIA, Terminal-Bench, how to read vendor tables
Top Chinese AI companies 2026 — ModelScope / Qwen ecosystem map
What are AI agents? — agent loop fundamentals

Official: Hugging Face — InternScience/Agents-A1 · ModelScope model page · Technical report (arxiv:2606.30616)

Benchmark figures and sampling defaults reflect the InternScience model card as of June 30, 2026. MoE serving requirements and independent coding evals may differ — verify before production. Last updated: June 30, 2026.

Agents-A1: InternScience 35B MoE Agent Model — Long-Horizon Search, GAIA 96, and vLLM Setup

Related posts

Apodex 1.0-mini: 35B Open Model Tops FutureX — Beats Sonnet 4.6 and GPT-5.5

Hermes WebUI: The Self-Hosted AI Agent Interface That Remembers Everything (2026 Complete Guide)

LongCat-2.0: Meituan's 1.6T MoE Open Model Trained on AI ASIC Superpods