Ali Asgarov, Umid Suleymanov, Aadyant Khatri · Oct 31, 2025 · Citations: 0
Automatic MetricsMathCoding
We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents to independently reason, perform targeted searches, and synthesize findings…
When evaluated on challenging benchmarks such as MATH500, AIME, and PhD-level science QA GPQA, SIGMA consistently outperforms both open- and closed-source systems, achieving an absolute performance improvement of 7.4%.
This paper proposes Group-relative Implicit Fine-Tuning (GIFT), a reinforcement learning framework for aligning large language models (LLMs) that unifies on-policy optimization with implicit preference learning.
Results show that GIFT converges faster, generalizes better with reduced overfitting, and outperforms GRPO on mathematical reasoning benchmarks (GSM8K, MATH, AIME) as well as generation tasks' evaluations (AlpacaEval and Arena-Hard).
Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li · Oct 9, 2025 · Citations: 0
Llm As JudgeAutomatic MetricsMathCoding
Our method features a specialized judge model trained with out-of-distribution data (AIME 2022, AIME 2023, and MATH 500) using oversampling techniques to accurately predict answer equivalence from partial reasoning traces, achieving 0.7072…
Comprehensive evaluations across three challenging benchmarks (AIME 2024, AIME 2025, and GPQA) and multiple reasoning models demonstrate that DeepPrune achieves remarkable token reduction of 65.73%--88.50% compared to conventional consensus…
Across seven mathematical benchmarks, LightReasoner improves accuracy by up to 28.1%, while reducing time consumption by 90%, sampled problems by 80%, and tuned token usage by 99%, all without relying on ground-truth labels.
Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu · Oct 9, 2025 · Citations: 0
Rubric RatingAutomatic MetricsMathLaw
Through a systematic analysis with human verification, we establish a taxonomy of these failure modes, identifying patterns like Miracle Steps-abrupt jumps to a correct output without a valid preceding derivation.
When integrated into an RL pipeline, RRM-based training consistently outperforms outcome-only supervision across four math benchmarks.
Beyond structured math tasks, FOR-Prompting supports refinement in open-ended and multi-stage tasks: qualitative analysis shows improved exploration, coverage, and specificity, and a blind study of human preferences found that participants…
The protocol is model-agnostic and operates purely through role-structured prompting, requiring no training, access to model internals, or symmetrically strong agents.
Jacqueline Maasch, John Kalantari, Kia Khezeli · Sep 3, 2025 · Citations: 0
DemonstrationsMath
As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4)…
In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge.
LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2)…
Lishui Fan, Yu Zhang, Mouxiang Chen, Zhongxin Liu · Aug 7, 2025 · Citations: 0
Pairwise PreferenceMathCoding
Additionally, to assess the reward model's discriminative capability in assessing reasoning-process quality, we introduce LiveCodeBench-RewardBench (LCB-RB), a new benchmark comprising preference pairs of superior and inferior reasoning…
Experimental results across HumanEval(+), MBPP(+), LiveCodeBench, and BigCodeBench show that a 7B model trained with ReCode outperforms the base version by 16.1% and reaches performance comparable to GPT-4-Turbo.
We evaluate MLLM verifiers across web navigation, computer use, and robotics, spanning 13+ models, 28+ designs, and thousands of trajectories from diverse agents.
Our methods yield more human-aligned verifiers, improving failure detection by 25pp and accuracy by 14pp.
To address this, we introduce Single-Pass Annotation with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation by jointly aligning solution steps to reference solutions and determine…
On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only \sim16% of training samples compared to human-labeled and other synthetically trained baselines.
Prince Kumar, Rudra Murthy, Riyaz Bhat, Danish Contractor · May 23, 2025 · Citations: 0
DemonstrationsMathCoding
We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.
Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on…
Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Ryan Chin, Caiming Xiong · May 21, 2025 · Citations: 0
Critique EditAutomatic MetricsMathCoding
Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks.
It achieves substantial average accuracy improvements of up to 16.69% on reasoning, 16.66% on coding, and 5.45% on agentic tasks, while maintaining cost efficiency.
Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian, Yu Wang · May 5, 2025 · Citations: 0
Pairwise PreferenceRubric RatingMathCoding
Reward modeling is essential for aligning large language models with human preferences through reinforcement learning.
Empirically, our models achieve superior performance across three reward model benchmarks on average, outperforming much larger open-weight models (e.g., INF-ORM-Llama3.1-70B) and proprietary ones (e.g., GPT-4o) by up to 4.9%.
