The whole dayTue 17 Nov 2026
AI Compass
WeeklyArchiveAbout

Hugging Face releases Qwen3.8-27B-pi-adapted RL LoRA harness adapter

Open-weight TRL adapter from harness-hub on the Hugging Face Hub uses safeagents rule checks to lift SWE-bench Pro Hard 51 pass@1 from 29.4% to 62.7% on 17 November 2026.

Hugging Face Harness Adapters graphic showing concentric orbital rings for Hermes, opencode, pi, LFM2.5-24B, LFM3 and TwIL-8B next to the Hugging Face mascot
Image: Hugging Face

Hugging Face’s harness-hub team released open-weight Qwen3.8-27B-pi-adapted and its safe reinforcement learning methodology on 17 November 2026, training lightweight per-harness LoRA adapters directly inside unmodified local coding harnesses including pi, opencode and hermes. Building on earlier LFM2.5-24B-A2B, LFM3-1.7B and TwIL-8B runs alongside Hub OpenRouter inference routing, one shared base server can host adapters for multiple agent harnesses simultaneously.

Repo2RLEnvs trajectory tasks, safeagents proxy and pi coding benchmarks

Training mixes SmolDataEnvs with Repo2RLEnvs, which converts open-source coding sessions shared on the Hugging Face Hub into verifiable build-heavy RL environments. Every tool call passes through safeagents, a deterministic rule-based proxy running in 10 to 20 ms that blocks reward-hacking shortcuts and assigns violating rollouts a zero score.

Served over the openai-completions endpoint via vLLM, Transformers or llama.cpp, Qwen3.8-27B-pi-adapted raised pass@1 on SWE-bench Pro (Hard 51) from 29.4% to 62.7% and on Terminal-Bench 2.1 from 39.5% to 55.8%, while cutting tool calls per task by 55% to 62%.

Technical details

Released model repo
harness-hub/Qwen3.8-27B-pi-adapted (open-weight RL LoRA adapter for the pi coding agent)
Benchmark gains (pass@1)
SWE-bench Pro (Hard 51) 29.4% to 62.7%; Terminal-Bench 2.1 39.5% to 55.8%; 55% to 62% fewer tool calls
RL environment and safety stack
Repo2RLEnvs + SmolDataEnvs in TRL; safeagents rule-based tool proxy (10-20 ms per check)
Serving engines and protocol
Transformers, vLLM, llama.cpp and macOS Llama.app using api set to openai-completions

Release details & context

Why openai-completions configuration and micro-batch packing matter

On the model card, harness-hub notes that pi users must configure their local provider with api set to openai-completions rather than the default Responses API format, because Qwen3.8-27B-pi-adapted was trained and evaluated exclusively against Chat Completions tool formatting.

During TRL training, finished agent trajectories pack into four micro-batches up to 131,072 tokens for 24B-class runs and 65,536 tokens for 8B-class runs, enabling even non-agent reasoning checkpoints such as TwIL-8B to acquire multi-step tool habits without modifying the surrounding CLI harness.

Common questions

Why must pi users set api to openai-completions when running Qwen3.8-27B-pi-adapted?

Without setting api to openai-completions, the pi coding agent defaults to the Responses API schema, which this LoRA adapter was neither trained nor evaluated against.

Hugging Face release timeline (4 launches tracked)

  1. Earlier22 Oct 2026
    Hugging Face releases Carbon-X, a 14.8B DNA-and-English language model

    Hugging Face Biology Research released Carbon-X (HuggingFaceBio/Carbon-X), a 14.8B DNA model averaging 66.7% across five benchmarks vs 67.5% for GPT-6.1 Sol.

  2. Earlier5 Nov 2026
    Hugging Face publishes open-source Mixture-of-Experts training guide based on 800k GPU hours

    Hugging Face published The Ultimate MoE Training Handbook, a 70k-word open guide with 55 interactive figures distilling 800k GPU hours of MoE experiments.

  3. Earlier16 Nov 2026
    Hugging Face routes Hub open-model inference through OpenRouter

    Hugging Face switches Hub chat-model Inference Providers to OpenRouter across 80+ hosts with automatic failover, zero markup and Bucket traces.

Explore the full Hugging Face dossier or browse all open source releases.

Also in the Tuesday 17 November edition

Read all 18 launches on one page
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
  10. 11
  11. 12
  12. 13
  13. 14
  14. 15
  15. 16
  16. 17
  17. 18

Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X