Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision

• URL: http://arxiv.org/abs/2602.12164v1
• Date: Thu, 12 Feb 2026 16:46:00 GMT
• Title: Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision
• Authors: Xiaohan He, Shiyang Feng, Songtao Huang, Lei Bai, Bin Wang, Bo Zhang,
• Abstract summary: Sci-CoE is a two-stage scientific co-evolving framework that enables models to self-evolve as both solver and verifier.<n>In the first stage, the model uses a small set of annotated data to establish correctness judgment anchors for the Verifier.<n>In the second stage, we introduce a geometric reward mechanism that jointly considers consensus, reliability, and diversity, driving large-scale self-iteration.
• Score: 15.806243963561776
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated exceptional reasoning capabilities, and co-evolving paradigms have shown promising results in domains such as code and math. However, in scientific reasoning tasks, these models remain fragile due to unreliable solution evaluation and limited diversity in verification strategies. In this work, we propose Sci-CoE, a two-stage scientific co-evolving framework that enables models to self-evolve as both solver and verifier through a transition from sparse supervision to unsupervised learning. In the first stage, the model uses a small set of annotated data to establish fundamental correctness judgment anchors for the Verifier. In the second stage, we introduce a geometric reward mechanism that jointly considers consensus, reliability, and diversity, driving large-scale self-iteration on unlabeled data. Experiments on several general scientific benchmarks demonstrate that Sci-CoE enhances complex reasoning capabilities and exhibits strong scalability, facilitating the construction of more robust and diverse evaluation systems. Codes are available at https://github.com/InternScience/Sci-CoE.

Related papers

• Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science [70.3658845234978]
  Large Language Models (LLMs) have greatly extended the capabilities of Multi-Agent Systems (MAS)<n>Despite this rapid progress, the field still relies heavily on empirical trial-and-error.<n>This bottleneck stems from the ambiguity of attribution.<n>We propose a factor attribution paradigm to systematically identify collaboration-driving factors.
  arXiv  Detail & Related papers  (2026-02-05T04:19:52Z)
• SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence [60.202862987441684]
  We introduce scientific instruction following: the capability to solve problems while strictly adhering to the constraints that establish scientific validity.<n>Specifically, we introduce SciIF, a multi-discipline benchmark that evaluates this capability by pairing university-level problems with a fixed catalog of constraints.<n>By measuring both solution correctness and multi-constraint adherence, SciIF enables finegrained diagnosis of compositional reasoning failures.
  arXiv  Detail & Related papers  (2026-01-08T09:45:58Z)
• Evaluating Large Language Models in Scientific Discovery [91.732562776782]
  Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge.<n>We introduce a scenario-grounded benchmark that evaluates LLMs across biology, chemistry, materials, and physics.<n>The framework assesses models at two levels: (i) question-level accuracy on scenario-tied items and (ii) project-level performance.
  arXiv  Detail & Related papers  (2025-12-17T16:20:03Z)
• Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis [0.0]
  This work conceptualizes an inverse approach to code design: a first-principles (or primitives)-centric, multi-agent system in which human expert knowledge is encoded as unit-physics tests that explicitly constrain code generation.<n>As datasets and models evolve, zero-shot code accuracy will improve; however, the Chain of Unit-Physics framework goes further by embedding first-principles analysis that is foundational to scientific codes.
  arXiv  Detail & Related papers  (2025-11-30T18:16:50Z)
• SCI-Verifier: Scientific Verifier with Thinking [37.08904000514563]
  Large language models (LLMs) are increasingly applied to scientific reasoning.<n>Existing verification studies in scientific domains suffer from two major limitations.<n>We propose solutions at both the data and model levels.
  arXiv  Detail & Related papers  (2025-09-29T04:58:43Z)
• A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
  Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
  arXiv  Detail & Related papers  (2025-08-28T18:30:52Z)
• Coding Triangle: How Does Large Language Model Understand Code? [33.42334127806147]
  Large language models (LLMs) have achieved remarkable progress in code generation, yet their true programming competence remains underexplored.<n>We introduce the Code Triangle framework, which systematically evaluates LLMs across three fundamental dimensions: editorial analysis, code implementation, and test case generation.
  arXiv  Detail & Related papers  (2025-07-08T16:20:43Z)
• Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team [53.38438460574943]
  IDVSCI is a multi-agent framework built on large language models (LLMs)<n>It incorporates two key innovations: a Dynamic Knowledge Exchange mechanism and a Dual-Diversity Review paradigm.<n>Results show that IDVSCI consistently achieves the best performance across two datasets.
  arXiv  Detail & Related papers  (2025-06-23T07:12:08Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)

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.