Skip to content
AI News HubLIVE
Original source2 min read

Reinforcement Learning with Decomposed Subtasks

Summary

arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout into a single scalar trajectory reward before it enters the policy update. When the task composes distinct skills, especially under sparse and delayed environmental feedback, this collapsing is lossy: the optimizer must implicitly infer which competency drove the outcome and how that should change behavior. We argue the right primitive is not a better scalar but a decomposition: trajectory reward should be split along subtasks before it enters the policy update. We introduce Reinforcement Learning with Decomposed Subtasks (RLDS), whose core is Subtask-Decomposed Advantage Estimation (SDAE): a…

SourcearXiv AIAuthor: Mattie Terzolo, Mikolaj Sacha, Ayan Sinha, Andrew Rabinovich
Reinforcement Learning with Decomposed Subtasks
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Sep 2026]

Title:Reinforcement Learning with Decomposed Subtasks

View a PDF of the paper titled Reinforcement Learning with Decomposed Subtasks, by Mattie Terzolo and 3 other authors

View PDF HTML (experimental)

Abstract:Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout into a single scalar trajectory reward before it enters the policy update. When the task composes distinct skills, especially under sparse and delayed environmental feedback, this collapsing is lossy: the optimizer must implicitly infer which competency drove the outcome and how that should change behavior. We argue the right primitive is not a better scalar but a decomposition: trajectory reward should be split along subtasks before it enters the policy update. We introduce Reinforcement Learning with Decomposed Subtasks (RLDS), whose core is Subtask-Decomposed Advantage Estimation (SDAE): a replacement for the scalar GRPO advantage that splits trajectory reward into per-subtask shares on a fixed taxonomy, computes a group-relative advantage per subtask, and distributes per-token credit by weighting each subtask's advantage by its importance, concentrating it around the step where a reflection marks that subtask's execution as consequential. We evaluate on four agentic benchmarks: FrozenLake (sparse grid navigation), HotpotQA (multi-hop QA, one retrieval tool), ScienceWorld (long-horizon embodied science), and DeepResearch (long-form research, four tools, composite rubric reward). Heterogeneity diagnostics emitted during training show where decomposition pays off - gains scale with subtask heterogeneity, largest on the high-heterogeneity tasks ScienceWorld (+11.5 points, paired-bootstrap 95% CI [+9.8, +13.3]) and FrozenLake (+9.8 points, [+7.0, +12.8]), and within noise on HotpotQA and DeepResearch, where the diagnostics predicted little to recover. ScienceWorld is also more compute-efficient under RLDS than scalar GRPO (-10.9% wall-clock per step), as long rollouts amortize the fixed reflect-and-grade overhead.

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2609.27035 [cs.AI]

(or arXiv:2609.27035v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.27035

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mattie Terzolo [view email] [v1] Tue, 22 Sep 2026 20:30:26 UTC (402 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Reinforcement Learning with Decomposed Subtasks, by Mattie Terzolo and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire…

Highlights and analysis are generated automatically and may contain errors. Check the original source.