CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs

[2608.14791] CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14791 (cs) [Submitted on 14 Aug 2026] Title: CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs Authors: Moein Salimi , Danial Parnian , Shaygan Adim , Amirmohammad Ebrahiminasab , Nima Alighardashi , Parsa Gholami , Sahand Akramipour , Mahdi Jafari Siavoshani , Mohammad Hossein Rohban View a PDF of the paper titled CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs, by Moein Salimi and 8 other authors View PDF HTML (experimental) Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to scientific discovery. Yet LLM research has mostly studied abduction through narrow, task-specific benchmarks, making it unclear whether observed gains transfer beyond the benchmark family used for training or evaluation. We ask whether RL post-training can improve abduction as a transferable reasoning capability. We introduce CEDAR-GRPO, a process-aware framework that combines final-answer correctness with abductive rewards for evidence coverage and evidence-to-explanation directionality. Four open-weight LLMs are post-trained on a controlled, domain-neutral mixture of abductive hypothesis-generation and hypothesis-selection tasks. We evaluate them on 11 unseen tasks spanning hypothesis selection, missing-fact generation, defeasible inference, long-context investigation, clinical reasoning, code debugging, and non-abductive controls. CEDAR- GRPO improves every model on every held-out task over both base models and correctness-only GRPO, with average gains of 7.4 and 2.7 points, respectively, and a maximum gain of 30.8 points. Ablations confirm that RL, abductive reward design, and task diversity each contribute to transfer. Process-level metrics further show stronger abductive behavior, including exploration of alternatives, elimination of rivals, backtracking, and uncertainty marking. Comments: Code and data are available at this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.14791 [cs.AI] (or arXiv:2608.14791v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14791 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Mohammad Hossein Rohban [ view email ] [v1] Fri, 14 Aug 2026 18:02:07 UTC (1,314 KB) Full-text links: Access Paper: View a PDF of the paper titled CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs, by Moein Salimi and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark 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? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning#627687
• An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models#1108898
• Toward aitiopoietic cognition: bridging the evolutionary divide between biological and machine-learned causal systems.#305278
• Natural Language and Everyday Reasoning#769505
• Cartesian equivariant representations for learning and understanding molecular orbitals#464477