From 25f9451405306964c3ced1646a6e64bac29e0aec Mon Sep 17 00:00:00 2001 From: sitabulaixizawaluduo Date: Fri, 5 Jun 2026 17:24:00 +0800 Subject: [PATCH 1/2] docs(roadmap): add 2026 Q2 and H2 milestones Add the 2026 Q2 (#1302) and 2026 H2 (#1381) milestone trackers to ROADMAP.md so the file reflects the latest planning. Existing Q1 and historical sections are preserved; "Last Updated" bumped to 2026-06-05. Refs: #1302, #1381 --- ROADMAP.md | 121 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 120 insertions(+), 1 deletion(-) diff --git a/ROADMAP.md b/ROADMAP.md index fc9bd7f88..119a22f46 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -7,6 +7,125 @@ direction of the project. **Latest Release:** Check [releases](https://github.com/areal-project/AReaL/releases) for the most recent version. +## 2026 H2 Roadmap (due December 31, 2026) + +[GitHub Issue #1381](https://github.com/areal-project/AReaL/issues/1381). + +This roadmap tracks major planned enhancements for the second half of 2026. Items are +organized into two categories: + +- **On-going:** Features currently under active development by the core AReaL team +- **Planned but not in progress:** Features that are good to have but currently lacking + bandwidth + +We use `[CC]` to mark items suitable for community contributions. If you're interested +in contributing, please reach out to discuss implementation details. + +### Backends + +**On-going** + +- [ ] Support training the latest large MoE models with the Megatron backend (including + Kimi 2.5 / GLM 5 / DeepSeek V3 / Qwen 3.6, etc.) + ([#1372](https://github.com/areal-project/AReaL/pull/1372), + [#1373](https://github.com/areal-project/AReaL/pull/1373)) +- [ ] More distribution strategies for colocated deployment + +**Planned but not in progress** + +- [ ] Omini model RL support with FSDP backend +- [ ] Proxy server support via RayScheduler (HTTP launcher actor) `[CC]` +- [ ] Weight delta update with `awex` +- [ ] Memory service for self-evolving agent + +### Usability + +**On-going** + +- [ ] Effective AReaL CLI support + ([#1374](https://github.com/areal-project/AReaL/issues/1374)) +- [ ] Profiling toolkit (distributed trace) +- [ ] Online RL training example based on AReaL 2.0 architecture + +**Planned but not in progress** + +- [ ] More RL post-training paradigms: IcePop Plus algorithm (verified in Ling MoE + training) and stepwise reward rubrics +- [ ] GUI Agent VLM training example +- [ ] OS-bench VLM training example `[CC]` +- [ ] Diffusion image/video generation model RL post-training `[CC]` +- [ ] Comprehensive LoRA support over the existing policy model training +- [ ] AReaL autopilot (automatic performance-optimized RL deployment suggestions and + systematic bottleneck analysis) + +### Documentation + +**Planned but not in progress** + +- [ ] Explain benchmarking results from nightly CI and how to extract issues + +## 2026 Q2 Roadmap (due July 31, 2026) + +[GitHub Issue #1302](https://github.com/areal-project/AReaL/issues/1302). + +This roadmap tracks major planned enhancements through July 31, 2026. Items are +organized into two categories: + +- **On-going:** Features currently under active development by the core AReaL team +- **Planned but not in progress:** Features that are good to have but currently lacking + bandwidth + +We use `[CC]` to mark items suitable for community contributions. If you're interested +in contributing, please reach out to discuss implementation details. + +### Backends + +**On-going** + +- [ ] Full training example with AReaL 2.0 architecture +- [ ] Deprecate support for SPMD mode (launcher, sglang/vllm server, etc.) +- [ ] Initial support of colocation weight transfer with `awex` + +**Planned but not in progress** + +- [ ] Migrate primary Megatron integration lib from `mbridge` to `megatron-bridge` + ([#1260](https://github.com/areal-project/AReaL/issues/1260)) `[CC]` +- [ ] Full support for colocation/separation weight transfer with `awex` as the backend + (`areal/experimental/weight_update/`) `[CC]` +- [ ] Migrate legacy NCCL broadcast weight transfer approach from `areal/engine` into + `areal/experimental/weight_update/` `[CC]` +- [ ] Omini model RL support with FSDP backend + ([#879](https://github.com/areal-project/AReaL/issues/879)) `[CC]` +- [ ] Support training the latest large MoE models with the Megatron backend, including + dpsk-v3/v4, Kimi-2.5, GLM-4/5 `[CC]` +- [ ] Native Kubernetes (K8S) scheduler `[CC]` + +### Usability + +**On-going** + +- [ ] Nightly CI workflow for performance benchmarking + ([#1284](https://github.com/areal-project/AReaL/issues/1284)) +- [ ] Refactor unit tests for faster execution + +**Planned but not in progress** + +- [ ] OS-bench VLM training example `[CC]` +- [ ] Multi-agent training example (single LLM, different prompts, e.g., planner agent + with sub-agents) `[CC]` +- [ ] Migrate legacy multi-turn agent examples to new API (`agenerate` → `ArealOpenAI` + or URL-based `AgentWorkflow`) `[CC]` +- [ ] Publish PyPI packages and CLI for running experiments +- [ ] Support distributed training and debugging in Jupyter notebooks +- [ ] Implement controller construction with model-centric API similar to `transformers` + +### Documentation + +**Planned but not in progress** + +- [ ] Explain benchmarking results from nightly CI and how to extract issues +- [ ] Document AReaL 2.0 architecture + ## 2026 Q1 Roadmap (due April 30, 2026) [GitHub Issue #907](https://github.com/areal-project/AReaL/issues/907). @@ -207,7 +326,7 @@ agentic AI systems** that is: ______________________________________________________________________ -**Last Updated:** 2026-02-06 +**Last Updated:** 2026-06-05 **Questions about the roadmap?** Open a discussion in [GitHub Discussions](https://github.com/areal-project/AReaL/discussions) or ask in our From a9cf3db46c093568e908b538ee00c246b380cb30 Mon Sep 17 00:00:00 2001 From: sitabulaixizawaluduo Date: Fri, 5 Jun 2026 17:30:15 +0800 Subject: [PATCH 2/2] docs(roadmap): fix Omni -> Omini in Q1 entry for consistency --- ROADMAP.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ROADMAP.md b/ROADMAP.md index 119a22f46..09c64d94a 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -147,7 +147,7 @@ organized into two categories: **Planned but not in progress** - [ ] Support for agentic training with large VLM MoE models (Archon backend) -- [ ] Omni model RL support with FSDP/Archon backend +- [ ] Omini model RL support with FSDP/Archon backend - [ ] Decoupling agent service from the inference service - [ ] Online RL training with the proxy server - [ ] LoRA support for the Archon backend