v0.5.7

Release Highlights

What's Changed

• fix: Bump minimum openai version to 2.14.0 (#504)
• Release v0.5.6 (#502)
• fix: Pin vLLM to 0.13.0 (#501)

Full Changelog: v0.5.6...v0.5.7

v0.5.6

Release Highlights

What's Changed

• fix: Pin vLLM to 0.13.0 (#501)
• release: Bump version to 0.5.5 (#500)
• feat: Add support for a LocalBackend Tinker model service (#499)

Full Changelog: v0.5.5...v0.5.6

v0.5.5

Release Highlights

What's Changed

• feat: Add support for a LocalBackend Tinker model service (#499)
• feat: Default loss to CISPO (#498)
• refactor: Remove coupled Unsloth service, upgrade to vLLM 0.11+ (#497)
• Deploy to model name + " (deployment)" (#496)
• Support more LoRA models in WandbDeploymentConfig (#495)
• Log metrics horizontally in W&B to simplify comparison to future runs (#494)
• Return 0th checkpoint (#492)
• Ensure bucket exists before pushing model weights (#491)
• Release v0.5.4 (#488)
• Revert "Update version to 0.5.4" (#487)
• Update version to 0.5.4 (#485)

Full Changelog: v0.5.4...v0.5.5

v0.5.4

Release Highlights

This patch release adds checkpoint download functionality and includes fixes for SkyPilot and package configuration.

New Features

• Download Checkpoint: Much simpler workflow for downloading checkpoints from training runs

Bug Fixes

• Fixed --system flag for uv pip install on SkyPilot backend
• Replaced deprecated uv.dev-dependencies with dependency-groups in package configuration

What's Changed

• Add download checkpoint functionality (#464)
• fix: add --system flag to uv pip install for SkyPilot backend (#462)
• fix: replace deprecated uv.dev-dependencies with dependency-groups (#484)

Full Changelog: v0.5.3...v0.5.4

v0.5.3

Release Highlights

What's Changed

• Release version 0.5.2 (#457)
• Remove openpipe dependency (#456)
• Add strip_logprobs utility function (#455)
• fix: Handle RULER rewards when all trajectories are identical (#454)
• Make copy.copy work for trajectories (#453)
• Fix lint (#451)
• feat: Add OpenEnv integration example (#445)
• Release v0.5.1 (#442)

Full Changelog: v0.5.1...v0.5.3

v0.5.1

Release Highlights

What's Changed

• Record auto_metrics on trajectory (#440)
• Fix ruff formatting (#438)
• Document Qwen3 14B instead of Qwen2.5 14B in non-tutorial examples (#437)
• Small docs change (#433)
• Serverless documentation (#432)
• Retry GET and DELETE (#431)
• Release v0.5.0 (#428)
• Release v0.4.12 (#427)
• feat: Add VLM support (#412)

Full Changelog: v0.5.0...v0.5.1

v0.5.0

Release Highlights

What's Changed

• Release v0.4.12 (#427)

Full Changelog: v0.4.12...v0.5.0

v0.4.12

Release Highlights

What's Changed

• Add client-side error capturing (#426)
• Send wandb-artifact:/// prefix as part of inference name. (#425)
• Report serverless metrics (#424)
• feat: Add placeholder _log() implementation for ServerlessBackend (#422)
• Upgrade SkyPilot to 0.10.3.post1 (#421)
• fix: exit the loop in the monitor_openai_server (#418)
• feat: Upgrade Unsloth (#408)
• add playwright agent example to dev/ART (#402)
• feat: Update SkyPilot to 0.10.2 (#393)
• Update training details (#389)
• LocalBackend._monitor_openai_server improvement (#388)
• Add RULER scoring to LG integration example (#385)
• Show open deep research tutorial (#384)
• Minor open deep research doc edits (#383)
• Add deep research tutorial (#382)
• Show GSPO docs page (#381)
• Add MCP•RL doc, remove GSPO (#380)
• Add news item on LangGraph (#379)
• gather_trajectory_groups: fused after_each callback to group await (#378)
• Document RULER in README (#376)
• Release v0.4.11 (#374)
• Pin gql verion to fix (#372)
• Update nb links (#371)
• Allow run_checks.sh to succeed on mac (#370)
• Add art.mcp package, release 0.4.10 (#369)

Full Changelog: v0.4.11...v0.4.12

v0.4.11

Release Highlights

This patch release includes bug fixes, documentation improvements, and a new MCP package:

New Features

• MCP Package: Added art.mcp package for Model Context Protocol integration

Bug Fixes

• Fixed GraphQL dependency compatibility by pinning gql package to < 4
• Fixed run_checks.sh script to succeed on macOS

Documentation & Examples

• Updated notebook links and examples
• Improved LangGraph integration documentation
• Better documentation for wrap_rollout function

What's Changed

• Add art.mcp package (#369)
• Pin gql version to fix compatibility (#372)
• Allow run_checks.sh to succeed on mac (#370)
• Update nb links (#371)
• Properly document wrap_rollout (#368)
• Update LangGraph docs (#367)
• Link to LangGraph (#365)
• Update LangGraph integration doc (#363)

Full Changelog: v0.4.9...v0.4.11

v0.4.9 - LangGraph Integration

🕸️ LangGraph Integration - Build Smarter Multi-Step Agents

This release introduces seamless integration with LangGraph, enabling you to train sophisticated ReAct-style agents that improve through reinforcement learning without manual prompt engineering.

✨ Major Features

• 🆕 LangGraph Integration - Drop-in replacement for LangGraph's LLM initialization with automatic logging and trajectory capture
• 🔄 Multi-Step Agent Training - Train agents that reason, use tools, and adapt their behavior over time
• 📊 Auto Trajectory Generation - Automatic conversion of LangGraph agent executions into ART training data
• ⚡ RULER Compatibility - Use ART's general-purpose reward function without hand-crafted rewards

🔧 Improvements

• Type Safety - Enhanced type annotations and fixes for LangGraph integration
• Memory Management - Better CUDA cache management and garbage collection utilities
• Dependencies - Pinned litellm to version 1.74.1 for stability
• Code Quality - Refactored logger imports and async tokenizer methods

📚 Documentation & Examples

• New Documentation - Comprehensive LangGraph integration guide with examples
• Updated README - Featured LangGraph integration in main project description
• Example Notebook - ART•E LangGraph notebook for training email search agents
• License Updates - Updated third-party notices and licensing information

🔧 Code Example

import art
from art.langgraph import wrap_rollout, init_chat_model
from langgraph import create_react_agent

@wrap_rollout(model)
async def run_agent(scenario: str) -> art.Trajectory:
    agent = create_react_agent(init_chat_model(), tools)
    result = await agent.ainvoke({"messages": [("user", scenario)]})
    return art.Trajectory()  # Automatically captured

# Train with RULER - no reward engineering needed!
await art.train(model, reward_function="ruler")

🔗 Links

• 📖 LangGraph Integration Docs
• 🏋️ Try the Notebook