Papers with OpenAI o1
Revealing the Barriers of Language Agents in Planning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies show language agents lack human-level planning abilities . limitations and mechanisms to address them remain insufficiently understood . |
| Approach: | They apply a feature attribution study to identify key factors hindering agent planning . they identify the limited role of constraints and diminishing influence of questions . |
| Outcome: | The proposed model achieves 15.6% on a real-world planning benchmark. |
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from simple Chain-of-Thought (CoT) prompting to advanced, product-oriented solutions like OpenAI o1 . |
| Approach: | They propose a strategy that shifts image input to critical reasoning stages and compresses redundant visual tokens via dynamic pruning. |
| Outcome: | The proposed model achieves state-of-the-art on five mathematical reasoning benchmarks (+3.4% vs previous sota) and demonstrates iterative reasoning capabilities for complex multi-step tasks. |
ViLBench: A Suite for Vision-Language Process Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite its advantages, evaluation on PRMs remains less explored, especially in the multimodal domain. |
| Approach: | They propose to benchmark vision large language models as output reward models and process reward models as process-supervised reward models. |
| Outcome: | The proposed model outperforms both ORM and PRM on vision-language benchmarks and achieves an average improvement of 3.3% over standard CoT and up to 2.5% over its untrained counterpart on ViLBench. |
MMATH: A Multilingual Benchmark for Mathematical Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a benchmark for multilingual complex reasoning spans 374 high-quality math problems across 10 typologically diverse languages. |
| Approach: | They propose a benchmark for multilingual complex reasoning across 10 languages . they show reasoning in English and answering in target languages can enhance performance . |
| Outcome: | The proposed benchmark demonstrates that models with high-quality reasoning can perform in multiple languages. |
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)
Copied to clipboard
Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng
| Challenge: | Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity. |
| Approach: | They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging. |
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks fail to evaluate large language models' instruction-following capabilities . current benchmarks lack multilinguality, implicit constraints and multi-turn dialogue . |
| Approach: | a new benchmark is designed to evaluate large language models' instruction-following capabilities . the benchmark features input prompts across 12 languages and includes inter-instance multilingual instructions . |
| Outcome: | a new benchmark for large language models (LLMs) is designed to assess their performance in real-world settings. |
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reasoning models are limited by inefficiency and computational redundancy . PRISM-MCTS integrates a process reward model with a dynamic shared memory . |
| Approach: | They propose a reasoning framework that integrates a process reward model with a dynamic shared memory. |
| Outcome: | PRISM-MCTS integrates a process reward model with a dynamic shared memory . it halves trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1 . |
Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities, but they may still falter on more complex problems, making errors that disrupt their reasoning paths. |
| Approach: | They propose a framework that encourages favorable branches at each reasoning step while penalizing unfavorable ones, enhancing the model’s overall problem-solving performance. |
| Outcome: | The proposed framework improves reasoning performance on multi-step reasoning tasks such as math word problems and science-based exam questions. |
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)
Copied to clipboard
Huifeng Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Bo Zeng, Huaiyu.wh Huaiyu.wh, Tianqi Shi, Liangying Shao, Chenyang Lyu, Longyue Wang, Weihua Luo, Kaifu Zhang
| Challenge: | Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances. |
| Approach: | They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search. |
| Outcome: | The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME). |
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks (2025.acl-long)
Copied to clipboard
Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev
| Challenge: | Inference-Time Scaling is critical to the success of recent models such as OpenAI o1 and DeepSeek R1 . however, many techniques require tasks to have answers that can be verified . |
| Approach: | They use data to train dedicated Feedback and Edit Models capable of inference-time scaling for open-ended tasks. |
| Outcome: | The proposed model can reach SoTA performance on Arena Hard at 92.7 as of 5 Mar 2025. |