Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
This paper introduces a counterfactual comparison-based credit assignment framework for reinforcement learning in multi-step reasoning with LLMs. By sampling multiple reasoning trajectories under the same input and treating their differences as implicit approximations of alternative decisions, it constructs an implicit process-level advantage estimator that transforms sparse terminal rewards into step-sensitive learning signals. Based on this, Implicit Behavior Policy Optimization (IBPO) is proposed, which significantly improves training stability and performance upper bounds on mathematical and code reasoning benchmarks.
[2605.16302] Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
[Submitted on 20 Apr 2026]
Title:Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
View a PDF of the paper titled Reducing Credit Assignment Variance via Counterfactual Reasoning Paths, by Fei Ding and 5 other authors
View PDF HTML (experimental)
Abstract:Reinforcement learning for multi-step reasoning with large language models (LLMs) often relies on sparse terminal rewards, leading to poor credit assignment conditions where the final feedback is evenly propagated across all intermediate decisions. This results in high gradient variance, unstable training, and numerous ineffective updates, ultimately causing the model to fail and preventing sustained improvement. We introduce a counterfactual comparison-based credit assignment framework, which samples multiple reasoning trajectories under the same input. By treating their differences as an implicit approximation of alternative decisions, we construct an implicit process-level advantage estimator that transforms sparse terminal rewards into step-sensitive learning signals. Based on this, we propose Implicit Behavior Policy Optimization (IBPO), which significantly improves training stability and performance upper bounds on mathematical and code reasoning benchmarks, pointing to a promising direction for unlocking the performance potential of LLMs.
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2605.16302 [cs.LG]
(or arXiv:2605.16302v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.16302
arXiv-issued DOI via DataCite
Submission history
From: Zijian Zeng [view email] [v1] Mon, 20 Apr 2026 13:33:54 UTC (263 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Reducing Credit Assignment Variance via Counterfactual Reasoning Paths, by Fei Ding and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI cs.CL
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?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
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?)