Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training

• URL: http://arxiv.org/abs/2604.16723v1
• Date: Fri, 17 Apr 2026 21:54:15 GMT
• Title: Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
• Abstract summary: Reward hacking is where models exploit imperfect evaluation proxies to maximize scores without producing genuine scientific innovation.<n>We propose an RL framework explicitly tailored for high-quality scientific idea generation.<n>Our framework significantly outperforms state-of-the-art baselines across expert-evaluated metrics of novelty, feasibility, and effectiveness.
• Score: 5.60408836929398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational inefficiency. A critical bottleneck in applying Reinforcement Learning (RL) to this open-ended domain is reward hacking -- where models exploit imperfect evaluation proxies to maximize scores without producing genuine scientific innovation. To address these limitations, we propose an RL framework explicitly tailored for high-quality scientific idea generation. We propose the first multi-agent reward function designed to serve as a judge, decoupling methodological validation from implementation details while providing strict binary rewards that are robust to reward hacking. To effectively optimize against this sparse signal, we utilize an unbiased variant of Group Relative Policy Optimization to mitigate artificial length bias. We grounded our training in ICLR-320, a curated dataset of problem-solution pairs extracted from ICLR 2024 proceedings. Experiments demonstrate that our framework significantly outperforms state-of-the-art baselines across expert-evaluated metrics of novelty, feasibility, and effectiveness.

Related papers

• Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search [8.82040111147814]
  We present an end-to-end RLAIF framework to generate emphportable search queries.<n>This task introduces a highly adversarial reward surface where policy optimization exploits flaws in rubrics, resulting in verbatim-copying behaviors.<n>We show that introducing a rule-based reward floor to correct for rewards assigned to verbatim copying degenerates this failure mode, resulting in a substantial $+0.147$ quality improvement on a cross-family evaluation judge.
  arXiv  Detail & Related papers  (2026-06-25T17:09:12Z)
• Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs [53.412166189410904]
  We use supervised learning as a computational proxy to establish a hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs)<n>Motivated by this observation, we propose a novel optimistic actor-critic algorithm that relies solely on the policy evaluation oracle.<n>We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works.
  arXiv  Detail & Related papers  (2026-05-02T04:46:54Z)
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time [51.256131853751754]
  We show that teaching reward models to produce explicit, multi-dimensional critiques transforms them from passive evaluators into active optimization tools.<n>We introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data.<n>The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models.
  arXiv  Detail & Related papers  (2026-04-13T15:38:09Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Multimodal Reinforcement Learning with Agentic Verifier for AI Agents [131.46008226323423]
  Argos is a principled multimodal reward agent to train reasoning models for agentic tasks.<n>By leveraging our agentic verifier across both SFT data and RL training, our model achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-03T04:42:47Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• COPO: Consistency-Aware Policy Optimization [17.328515578426227]
  Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks.<n>Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging rule-based rewards as a low-cost alternative for computing advantage functions and guiding policy optimization.<n>We propose a consistency-aware policy optimization framework that introduces a structured global reward based on outcome consistency.
  arXiv  Detail & Related papers  (2025-08-06T07:05:18Z)
• Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner [31.033131727230277]
  Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL)<n>We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training.<n>Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines.
  arXiv  Detail & Related papers  (2025-07-31T07:54:58Z)
• LIRE: listwise reward enhancement for preference alignment [27.50204023448716]
  We propose a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework. LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm. Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks.
  arXiv  Detail & Related papers  (2024-05-22T10:21:50Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.