mlsanityData to 7 Oct 2026

Studying the Korean Word-Chain Game with RLVR: Mitigating Reward Conflicts via Curriculum Learning

arXiv 2510.03394 ↗First posted 3 Oct 2025cs.LG cs.CLcited by 0

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training large language models (LLMs) with stronger reasoning abilities. It has also been applied to a variety of logic puzzles. In this work, we study the Korean word-chain game using RLVR. We show that rule-derived rewards can naturally conflict, and demonstrate through experiments that a curriculum-learning scheme mitigates these conflicts. Our findings motivate further studies of puzzle tasks in diverse languages.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 17 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

11 of 17 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models24 Sep
  2. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning20 Feb
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan
  4. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Training22 Nov

Other references · 7

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 229
  4. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  5. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 121
  6. 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzlescited by 53
  7. 2024Curriculum Reinforcement Learning for Complex Reward Functionscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
  2. 2025Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation
  3. 2025The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
  4. 2026Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck
  5. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
  6. 2025From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR
  7. 2026To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
  8. 2026From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation