Climbing to the Search Frontier.
🤗 Collection | 💻 GitHub | 🔬 Evaluation Harness
## Introduction Iris-mini is an open-weight search agent post-trained from [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B). A capable search agent has to decide what to search, how to read what comes back, when to keep going, and when the evidence it has gathered is enough. Iris is trained for exactly that loop, through alternating rounds of supervised fine-tuning and reinforcement learning. Its larger sibling is [Iris-pro](https://huggingface.co/AllSpark-Research/Iris-pro) (397B-A17B). | | | | --- | --- | | Base | Qwen3.6-35B-A3B | | Parameters | 35B total / 3B active (256 experts, 8 active) | | Layers / hidden | 40 / 2048 | | Context | 256K | | Precision | bfloat16 | ## Performance Open-weight systems in the 30–35B range: | Model | Size | BrowseComp | BrowseComp-ZH | DeepSearchQA | HLE | | --- | --- | --- | --- | --- | --- | | MiroThinker-1.7-mini | 30B | 67.9 | 72.3 | – | 36.4 | | FORT-Searcher | 30B | 72.2 | 75.0 | – | – | | Apodex-1.0-mini | 35B | 71.5 | 80.6 | 82.2 | 46.8 | | Nex-N2-mini | 35B | 74.1 | 79.6r | 87.2r | 37.1r | | Agents-A1 | 35B | 75.5 | – | – | 47.6 | | XYZ-Aquila-mini | 35B | 78.8 | 82.9 | **89.5** | 51.1 | | **Iris-mini** | 35B | **82.2** | **84.8** | 86.9 | **52.3** | DeepSearchQA is scored with F1, the rest with accuracy; HLE uses the 2,158-question text-only subset. Iris numbers use the `discard-all` context-management setting; baselines come from their public reports, each under its own context management. r reproduced by the XYZ-Aquila team. ## Context management Long-horizon search runs out of context before a hard question is resolved, so a published number belongs to the agent *and* its harness. We report every benchmark in both regimes, under one tool set, one context limit and one judge. | Setting | BrowseComp | BrowseComp-ZH | DeepSearchQA | HLE | | --- | --- | --- | --- | --- | | w/o | 64.7 | 72.3 | 81.0 | 43.2 | | retry | – | 83.0 | 89.1 | 52.0 | | discard-all | 82.2 | 84.8 | 86.9 | 52.3 | | discard-all + retry | **85.9** | **85.1** | **89.9** | **52.4** | `discard-all` resets the conversation to the opening question once the prompt crosses a threshold. `retry` restarts an episode that ended without a parseable answer, carrying forward a short summary of what was already ruled out. We report `discard-all` as the headline setting even where adding `retry` scores higher. ## Quickstart Serve with SGLang: ```bash python -m sglang.launch_server \ --model-path AllSpark-Research/Iris-mini \ --served-model-name Iris-mini \ --port 21234 --tp-size 4 \ --context-length 262144 \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder ``` Then evaluate with [Iris-Harness](https://github.com/AllSpark-Research/Iris/tree/main/Iris-Harness), which reproduces the numbers above: ```bash bash scripts/run_eval.sh \ --base-url http://127.0.0.1:21234/v1 \ --llm-config iris-mini \ --benchmarks "browsecomp:0:1" \ --context-discard-threshold 131072 ``` The model is trained to call tools through the OpenAI function-calling interface and to wrap its final answer in `\boxed{}`. Prior reasoning is carried back into the conversation on each turn; the harness's `iris-mini` config sets this up for you. ## License Apache 2.0.