text string | source string |
|---|---|
latency. Moreover, as the num- ber and diversity of available LLMs continue to grow, it becomes critical to route queries to the most suitable model, effectively balancing perfor- mance with operational costs. 2.2 LLM Routing LLM routing seeks to identify the most suitable language model for a given query, with various... | https://arxiv.org/abs/2505.16303v1 |
two sets: Cx={c1, c2,··· |ci∈ C} : This set com- prises the capabilities deemed necessary to address query x, ranked in descending order of importance. Kx={k1, k2,··· | ki∈ K} : This set encom- passes the knowledge areas considered essential for resolving query x, also ranked in descending order of importance. Followin... | https://arxiv.org/abs/2505.16303v1 |
is computed analogously. Normalization across both knowledge and capability score calculations ensures that these two distinct types of scores are on a comparable scale, facilitating a balanced routing decision.The final routing decision is determined by the following algorithm: RMT(x) = arg max Mt∈MT(γKSα(Mt,x) +δCSα(... | https://arxiv.org/abs/2505.16303v1 |
updated benchmark with 18 tasks across 6 categories, including math, reasoning, coding, data analysis, language and instruction following. In the evaluation, we utilize the snapshot released on 2024-11-25. 4.2 Experiment Setup For the candidate models, we select eight high- performing LLMs: Gemini-1.5-Pro(Reid et al., ... | https://arxiv.org/abs/2505.16303v1 |
and Routing by Capability approaches also deliver strong results, consistently surpassing the best single model and significantly outperform- ing random routing on average. Notably, Routing byKnowledge excels in knowledge-intensive tasks, achieving the best score on GPQA and the second- best on MMLU-Pro. This underscor... | https://arxiv.org/abs/2505.16303v1 |
to changes in β. Specifically, the performance and cost metrics for LiveBench, a text generation benchmark, exhibit more pro- nounced variations in response to adjustments in β compared to those observed for GPQA, a question- answering benchmark. This suggests that text gen- eration tasks are more sensitive to the pric... | https://arxiv.org/abs/2505.16303v1 |
the distribution of generated knowledge highlights the RouteMix benchmark’s comprehensive span of knowledge domains, rang- ing from highly specific academic areas to practical applications. On datasets with broad knowledge requirements, such as MMLU-Pro, the generated knowledge exhibits a relatively balanced distribu- ... | https://arxiv.org/abs/2505.16303v1 |
deployment and effectiveness of InferenceDynamics in such real-application scenarios remains an important di- rection for future work. Addressing these limitations will be crucial for broadening the applicability and enhancing the ro- bustness of InferenceDynamics and similar LLM routing frameworks. Ethics Statement Ou... | https://arxiv.org/abs/2505.16303v1 |
as soft reasoners over language. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020 , pages 3882–3890. ijcai.org. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, C... | https://arxiv.org/abs/2505.16303v1 |
Leimberger, Ben Rossen, Ben Sokolowsky, Ben Wang, Benjamin Zweig, Beth Hoover, Blake Samic, Bob McGrew, Bobby Spero, Bogo Giertler, Bowen Cheng, Brad Lightcap, Brandon Walkin, Brendan Quinn, Brian Guarraci, Brian Hsu, Bright Kellogg, Brydon Eastman, Camillo Lugaresi, Car- roll L. Wainwright, Cary Bassin, Cary Hudson, C... | https://arxiv.org/abs/2505.16303v1 |
for Computational Linguistics. Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, and Deheng Ye. 2024b. More agents is all you need. CoRR , abs/2402.05120. Moxin Li, Yong Zhao, Yang Deng, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, and Tat-Seng Chua. 2024c. Knowledge boundary of large language models: A survey. CoRR ,... | https://arxiv.org/abs/2505.16303v1 |
Greg Durrett. 2025. To cot or not to cot? chain- of-thought helps mainly on math and symbolic rea- soning. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025 . OpenReview.net. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Se- bastian Gehrmann, Yi Tay, Hyung... | https://arxiv.org/abs/2505.16303v1 |
Zhe Su, Leander Maben, Raj Mehta, Wayne Chi, Lawrence Keunho Jang, Yiqing Xie, Shuyan Zhou, and Graham Neu- big. 2024. Theagentcompany: Benchmarking LLM agents on consequential real world tasks. CoRR , abs/2412.14161. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayi- heng Liu, F... | https://arxiv.org/abs/2505.16303v1 |
BigBench-Hard (Suzgun et al., 2023) Sample 40 instances from each cate- gory except weboflies, to avoid colli- sion with LiveBench. Formulate into MCQA for Yes/No and QA question. Remain the free-response question un- changed.Zero-shot CoTExact Match (EM) BigCodeBench (Zhuo et al., 2024) We directly use the BigCodeBenc... | https://arxiv.org/abs/2505.16303v1 |
Following Sprague et al. (2025), we employ GPT-4o-mini as LLM-as-a-Judge to evaluate the BigGen- Bench, and instances with a score larger than 4 is considered correct. The specific prompt is shown below: 15 Prompt for evaluation BigGenBench Task Description: An instruction (might include an Input inside it), a response... | https://arxiv.org/abs/2505.16303v1 |
explanation* for your selections or rankings. Example: Query: "Solve the following financial problem efficiently and clearly. Output the final answer as: boxedanswer. Where [answer] is just the final number or expression that solves the problem. Keep the answer to five decimal places if it is a number, and do not use p... | https://arxiv.org/abs/2505.16303v1 |
PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models Chenzhuo Zhao1*Ziqian Liu2*Xingda Wang1Junting Lu1 Chaoyi Ruan3† 1Peking University2Unaffiliated3National University of Singapore {cyzcz, nev_settle, aidan.lew.37}@stu.pku.edu.cn liuziqian25@gmail.com ruancy@comp.nus.edu.sg Abstract Prom... | https://arxiv.org/abs/2505.16307v1 |
process computationally expensive and less reliable. External scoring often lacks consis- tency or sufficient granularity, especially when re- lying on models to assess complex outputs. More- over, methods tend to specialize: some focus on supervised tasks with explicit labels, while others target alignment tasks defin... | https://arxiv.org/abs/2505.16307v1 |
ef- fort, they often rely on large models for generation and evaluation, limiting scalability in low-resource or small-model settings. Overall, this body of work underscores the importance of prompt formulation and motivates the development of more systematic and efficient optimization frameworks. 2.2 Prompt Optimizati... | https://arxiv.org/abs/2505.16307v1 |
of yiforxi. The language model M generates outputs with probabilities pM(y|x, P) conditioned on input xand prompt P. Our objec- tive is to derive an optimal prompt P∗that maxi- mizes the expected weighted log-probability, that is,E(x, y, r )∼ D[r·logpM(y|x, P)], where r can represent either a binary label or a scalar p... | https://arxiv.org/abs/2505.16307v1 |
a prompt P, input x, and expected output y, we define the token-level cross- entropy loss as: LCE(x, y,P, M) =−|y|X i=1logPM(yi|y<i, x,P) (3) where yiis the i-th token of the output sequence andy<idenotes all preceding tokens. The batch- 4 level loss over dataset Dis computed as: Lbatch(P, M) =1 nnX i=1LCE(xi, yi,P, M)... | https://arxiv.org/abs/2505.16307v1 |
token-level evaluation with multi-candidate scoring—offering a favorable efficiency-profile over generation- heavy methods such as OPRO or PromptWizard. Method Evaluation Level Candidate Count SPO Sequence-Level Single PromptWizard Sequence-Level Multiple EvoPrompt Sequence-Level Multiple OPRO Sequence-Level Single PMP... | https://arxiv.org/abs/2505.16307v1 |
optimization approaches: Opro, EvoPrompt, PromptWizard, TextGuard, and PromptBreeder, which leverage language models to search, mutate, or iteratively improve prompts without human intervention. Implementation Details. We conduct experi- ments using a mix of open-source and propri- etary language models, including Qwen... | https://arxiv.org/abs/2505.16307v1 |
Figure 3: Win rate comparisons on AlpacaEval 2.0. Left: original Qwen2.5-14B win rates across instruction sources. Right: PMPO-optimized results using the same model. Bottom: average win rates across models. These results show that PMPO enables mid- sized models like Qwen2.5-14B to produce com- petitive outputs, surpas... | https://arxiv.org/abs/2505.16307v1 |
4.5 Ablation Study To assess the contribution of individual components within PMPO, we conduct a cumulative ablation study on the BBH benchmark using Qwen2.5-14B for both optimization and evaluation. Specifically, we disable three key modules: Token Importance Masking (TIM), Bad Case Analysis (BCA), and Preference Loss... | https://arxiv.org/abs/2505.16307v1 |
Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, and 12 others. 2020. Lan- guage models are few-shot learners. Preprint , arXiv:2005.14165. Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, and Minlie Huang. 2023. Black-box prompt optimization: Aligning large la... | https://arxiv.org/abs/2505.16307v1 |
Advances in neural information processing systems , 35:24824– 24837. Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Fengwei Teng, Jinhao Tu, Xinbing Liang, Sirui Hong, Chenglin Wu, and Yuyu Luo. 2025. Self-supervised prompt opti- mization. arXiv preprint arXiv:2502.06855 . Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaop... | https://arxiv.org/abs/2505.16307v1 |
specifically for these examples. Instead: ,→ - Extract the underlying patterns and reasoning these examples demonstrate - Understand the general skills or knowledge being tested - Focus your prompt improvements on the task_description and solving the general problem First, analyze the prompt for: - Gaps in instruction ... | https://arxiv.org/abs/2505.16307v1 |
or examples. For each unit, consider whether masking (removing) it would leave the surrounding prompt logically coherent and understandable.,→ ,→ Your task: 1. Carefully read the current prompt: {prompt} 2. If possible, segment the prompt into up to 5 independent units. Only select units whose removal would not disrupt... | https://arxiv.org/abs/2505.16307v1 |
allow PMPO to optimize prompts for alignment-style objectives using cross-entropy on preferred vs. dispreferred completions. Note: * BBH refers to the complete set of 23 tasks in the BIG-Bench Hard benchmark. •Boolean Expressions: Evaluate the truth value of a random Boolean expression consisting of Boolean constants (... | https://arxiv.org/abs/2505.16307v1 |
enhances reasoning by encouraging the model to generate intermediate steps before the final answer. It improves performance in arithmetic and multi-step tasks by including phrases like “Let’s think step by step” to elicit structured reasoning chains. Step-Back (Zheng et al., 2023b). Step-Back prompting first guides the... | https://arxiv.org/abs/2505.16307v1 |
a way that is easier to understand, minimizing ambiguity and considering edge cases. And then provide a solution step by step for the question. A.3 Case Study Figure A5: Cross-entropy loss per iteration during prompt optimization on AQUA-RAT. To better understand how PMPO progressively improves prompt quality during op... | https://arxiv.org/abs/2505.16307v1 |
the derived conclusions and evaluate whether it satisfies the conditions of the problem. ,→ 4.Clearly explain the rationale behind selecting the correct answer option, detailing how the option meets the specified conditions. ,→ Ensure your response includes a clear explanation of the reasoning process used to arrive at... | https://arxiv.org/abs/2505.16307v1 |
the correct answer. 4. **Explain Your Reasoning** : Provide a clear and detailed explanation of your thought process and the steps taken to arrive at your solution. Justify why certain options are valid or invalid based on your calculations and reasoning. ,→ 17 Your response should demonstrate a deep understanding of t... | https://arxiv.org/abs/2505.16307v1 |
identified formulas to the given data, ensuring each step of the calculation is accurate and logically sound. ,→ 4. **Evaluate Answer Options** : Compare your calculated result against each provided answer option to determine the correct match. ,→ 5. **Select the Correct Answer** : Choose the answer option that precise... | https://arxiv.org/abs/2505.16307v1 |
outward. ,→ -**Operator Precedence** : Observe the correct order of operations: "not" has the highest precedence, followed by "and", and then "or". This ensures proper simplification of the expression. ,→ -**Logical Reasoning** : Clearly articulate the step-by-step logical reasoning applied during the evaluation proces... | https://arxiv.org/abs/2505.16307v1 |
,→ ,→ To accomplish this task effectively, follow these steps: 1.**Identify the Pronoun** : Locate the pronoun in the sentence. 2.**Analyze Context** : Carefully examine the sentence for any clues that might reveal the pronoun 's antecedent. Consider the logical relationship between the pronoun and all potential antece... | https://arxiv.org/abs/2505.16307v1 |
"valid" or "invalid". - Provide a concise but thorough explanation of your reasoning process. - Use clear and precise language to articulate your thoughts. BBH Prompt (geometric_shapes) Your task is to interpret an SVG path element specified within a "d" attribute and deduce the geometric shape that would be formed upo... | https://arxiv.org/abs/2505.16307v1 |
4. If the sequence is ambiguous after applying the clues, re-examine the descriptions for additional hints or rephrase the clues for clarity. ,→ 5. Provide a clear and concise answer detailing the order of the objects from left to right or top to bottom, depending on the orientation described. ,→ **Example Format** : Y... | https://arxiv.org/abs/2505.16307v1 |
your response is concise and focuses exclusively on identifying and listing the correct order of objects, without additional commentary or explanations unless required by the task. ,→ - Scenarios may involve various types of objects and different numbers of objects, but the core principle remains consistent: use the pr... | https://arxiv.org/abs/2505.16307v1 |
point. Follow these structured guidelines to methodically analyze the navigation instructions: ,→ **Guidelines for Analyzing Navigation Instructions:** 1.**Initial Setup** : Position the agent at the Origin (Point 0) and orient it Facing Forward. 2.**Command Handling** : -**Movement Commands** : Adjust the agent 's pos... | https://arxiv.org/abs/2505.16307v1 |
the provided description to familiarize yourself with each object and its corresponding color. ,→ 2.**Pinpoint the Object of Interest** : Identify which object 's color is being queried in the question. 3.**Retrieve the Color Information** : Refer back to your initial notes to locate the color associated with the objec... | https://arxiv.org/abs/2505.16307v1 |
which of the two given sentences is intended to convey sarcasm. Sarcasm is characterized by language that expresses a meaning opposite to its literal sense, often used to mock or criticize. ,→ ### Analytical Approach 1.**Analyze Word Choice and Sentence Structure** : Carefully examine the words and structure of each se... | https://arxiv.org/abs/2505.16307v1 |
other known limitations or rules (such as curfews). ,→ 4.**Define Availability Periods** : Clearly outline the identified periods of availability in your response, making sure they align with the provided schedule and any supplementary context. ,→ 25 5.**Use Concise Language** : Respond using clear, professional langua... | https://arxiv.org/abs/2505.16307v1 |
which these swaps take place. This meticulous documentation is essential for accurate tracking and proper application of each swap.,→ ,→ 3.**Step-by-Step Swap Execution** : Execute each swap operation strictly in the recorded sequence. Update the positions of the entities after every swap, maintaining an organized and ... | https://arxiv.org/abs/2505.16307v1 |
: Recognize that every individual in the scenario is consistently either truthful or deceitful. A truthful individual will never contradict themselves or anyone known to be truthful, whereas a deceitful individual will always contradict statements of truthfulness.,→ ,→ 2.**Identifying Assertions** : Closely examine eac... | https://arxiv.org/abs/2505.16307v1 |
loss over full reasoning sequences. Additionally, since AQUA-RAT is a multiple-choice task, we also support a preference-based training variant, where the correct answer choice is treated as the selected output and the incorrect options as rejected , allowing PMPO to operate under both supervised and preference paradig... | https://arxiv.org/abs/2505.16307v1 |
increase likelihood on rejected ones. This setup enables effective instruction tuning without requiring explicit gold answers. AlpacaEval Prompt To generate an informative, helpful, and accurate response to a user 's query, follow these steps carefully: 1.**Comprehend the Query** : Read the user 's question or request ... | https://arxiv.org/abs/2505.16307v1 |
next moves. ,→ These enhancements not only improve navigation accuracy but also provide a more intuitive and personalized experience for users. ,→ Analysis: For smaller models like Qwen2.5-0.5B, PMPO generates prompts that emphasize procedural redundancy and compensatory strategies (e.g., feedback loops, real-time upda... | https://arxiv.org/abs/2505.16307v1 |
will help track the user 's precise location throughout the journey. ,→ 3. **Update Coordinates According to Movements** : -Increase the X-coordinate for forward moves by the step count. -Decrease the X-coordinate for backward moves by the step count. -Decrease the Y-coordinate for leftward moves by the step count. -In... | https://arxiv.org/abs/2505.16307v1 |
arXiv:2505.16312v1 [cs.AI] 22 May 2025EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning Jiawei Liu1,2*, Qisi Chen1, Jianshu Zhang2, Quan Liu2, Defu Lian1†, 1University of Science and Technology of China,2iFLYTEK Research, {ljw1222,chisch}@mail.ustc.edu.cn liandefu@ustc.edu.cn Abstract ... | https://arxiv.org/abs/2505.16312v1 |
cal statements. Even domain-specific models like MathBERT (Peng et al., 2021), which enhance mathematical text representation, along with other embedding models MATH-Similarity (Steinfeldt and Mihaljevi ´c, 2024), lack optimization for identi- fying functional equivalence between mathematical sentences. This limitation... | https://arxiv.org/abs/2505.16312v1 |
to Qwen2.5-Math-7B-Instruct on GSM8K, EquivPruner not only cuts token consump- tion by a substantial 48.1% but also further boosts accuracy in a very high baseline. 2 Related Work LLM Reasoning via Search Strategies Efforts to improve LLM problem-solving capabilities have moved beyond simple prompting. Chain- of-Though... | https://arxiv.org/abs/2505.16312v1 |
Methodology 3.1 Define Semantic Equivalence in Mathematics Simply equating statements based on identical out- comes can be superficial and misleading, as it may overlook critical differences in conceptual articu- lation, structural formulation, symbolic interpre- tation, and methodological pathways. To address this, we... | https://arxiv.org/abs/2505.16312v1 |
it- erative calibration process yielded the MathEquiv dataset, characterized by high-quality labels and an accurate assessment of semantic equivalence. The 4 final prompt is detailed in Figure 4. The MathEquiv dataset is available at https://huggingface.co/ datasets/Jiawei1222/MathEquiv . 3.3 Lightweight Pruner for Tre... | https://arxiv.org/abs/2505.16312v1 |
detailed in Appendix A.1. 4.2 Experimental Setup 4.2.1 Models and Datasets For inference, we utilized several LLMs: Qwen2.5- Math-7B-Instruct (Yang et al., 2024), Mistral-7B- SFT (Shao et al., 2024), and Qwen2.5-Math-1.5B- Instruct (Yang et al., 2024). Given that exist- ing open-source PRMs are predominantly tailored f... | https://arxiv.org/abs/2505.16312v1 |
defined as the ratio of tokens gen- erated by the EquivPruner-enhanced search to those generated by the baseline MCTS. 4.4 Main Results Table 1 presents our main experimental findings, comparing vanilla MCTS against MCTS aug- mented with EquivPruner. The results consis- tently demonstrate that EquivPruner substantially... | https://arxiv.org/abs/2505.16312v1 |
kselection occurs. This process ensures that the kchosen candidates are more diverse, potentially leading to the discov- ery of more effective reasoning paths and thereby improving overall task performance. The results in Table 2 validate this. On MATH, EquivPruner increased accuracy from 82.00% to 82.20% (+0.20%), and... | https://arxiv.org/abs/2505.16312v1 |
significantly larger than the 7B parameter scale. Secondly, our work focused onEquivPruner ’s application at inference time, and its potential integration with iterative LLM train- ing or refinement strategies remains an area for future exploration. Lastly, while designed for gen- eralizability, our empirical validatio... | https://arxiv.org/abs/2505.16312v1 |
Yuri Burda, Harri- son Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let’s verify step by step. In The Twelfth Inter- national Conference on Learning Representations . Jieyi Long. 2023. Large language model guided tree-of- thought. arXiv preprint arXiv:2305.08291 . Lia... | https://arxiv.org/abs/2505.16312v1 |
Planning with large language models for code gener- ation. In The Eleventh International Conference on Learning Representations . A Experimental Details A.1 MathEquiv Dataset Generation Details The MathEquiv dataset was constructed as follows: Problem Sourcing and Splitting : We selected 7,500 problems from the MATH tr... | https://arxiv.org/abs/2505.16312v1 |
across baseline and EquivPruner-enhanced evaluations unless otherwise specified. Table 5: Step-level Beam Search (SBS) hyperparame- ters. Hyperparameter Value Beam Size 3 LLM Generation Temperature 0.7 LLM max_new_tokens 1024 Search Tree Maximum Width 10 Search Tree Maximum Depth 50 10 Please determine whether the foll... | https://arxiv.org/abs/2505.16312v1 |
arXiv:2505.16315v2 [cs.AI] 23 May 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning Xiaoxue Cheng1∗, Junyi Li2∗, Zhenduo Zhang3, Xinyu Tang1, Wayne Xin Zhao1†,Xinyu Kong3,Zhiqiang Zhang3 1Gaoling School of Artificial Intelligence, Renmin University of China 2Department of Computer Sci... | https://arxiv.org/abs/2505.16315v2 |
slow, deliberate thinking (System 2), we pose the following research question: Can LRMs learn to dynamically switch between fast and slow thinking modes based on task complexity, enabling more efficient and adaptive reasoning? In this paper, we propose Adaptive Cognition Policy Optimization ( ACPO ), a reinforcement le... | https://arxiv.org/abs/2505.16315v2 |
additional KL regularization term to stabilize optimization: JGRPO(θ) =E(q,a)∼D,{yi}G i=1∼πθold(·|q) " 1 GGX i=11 |yi||yi|X t=1 min ri,t(θ)ˆAi,t,clip ri,t(θ),1−ε,1 +ε ˆAi,t −βD KL(πθ||πref)!# ,(2) where ri,t(θ) =πθ(yi,t|q,yi,<t) πθold(yi,t|q,yi,<t)is the importance sampling ratio for the t-th token yi,t. 2.2 Token ... | https://arxiv.org/abs/2505.16315v2 |
slow thinking segments. To ensure the quality of the training data, we utilize the LIMO dataset [ 22], a carefully curated, high-quality dataset of complex mathematical 3 Query Response 1 Response 2 Response 3 Response N Longest Response ... ACPO Policy ModelDifficulty： Success Rate TLB： Avg Length Max Lengthy1 y2 y3 y... | https://arxiv.org/abs/2505.16315v2 |
including the online token length budget estimation and reward design that are specifically tailored for dynamic system switch. 4 3.2.1 Reward Design In this work, we adopt GRPO as the underlying RL algorithm, extending its framework with a customized reward structure to explicitly guide the model’s reasoning behavior.... | https://arxiv.org/abs/2505.16315v2 |
during optimization. In order to ensure that the reward for correct responses remains strictly positive and the reward for incorrect responses remains strictly negative, we apply max andmin operations to clip the final reward within the desired range. Based on the final reward, we leverage the GRPO objective in Eq. 2 t... | https://arxiv.org/abs/2505.16315v2 |
models are trained for one epoch, and both the SFT and RL stages are conducted using the VeRL framework [ 32]. We set pthresh= 0.5in Eq. 6 and set the reward weights as wacc= 0.6,wlen= 0.3, andwthink= 0.1in Eq. 7. 6 Table 3: Performance comparison between three reasoning models trained with GRPO and ACPO on the MATH 50... | https://arxiv.org/abs/2505.16315v2 |
for comparison in Table 3. From the results, we observe that both GRPO and ACPO can compress the reasoning length of the original models. In contrast, ACPO consistently achieves more significant compression, often 7 1 2 3 4 5 Difficulty050010001500200025003000Length ACPO-1.5B L1-Max L1-Exact 0.00.20.40.60.81.0 Accuracy... | https://arxiv.org/abs/2505.16315v2 |
e.g., 30, 60, 90) step by step, even after identifying a valid solution. This leads to a lengthy reasoning path with 1555 tokens, filled with redundant self- verification and repeated constraint checking. In contrast, the model trained with ACPO efficiently identifies the necessary constraints, rapidly filtering out in... | https://arxiv.org/abs/2505.16315v2 |
2 is \boxed{2220}. </answer> (1555 Tokens)<slow_think> Okay , so I need to find the smallest positive integer multiple of 30 that can be written using only the digits 0 and 2. Hmm, let's break this down. First, I know that 30 is 3 times 10, so any multiple of 30 must be divisible by both 3 and 10. That means the number... | https://arxiv.org/abs/2505.16315v2 |
and Slow Thinking in LLMs. The dual process theory [ 19] describes two modes of human thinking: fast, intuitive thinking (System 1) and slow, deliberate thinking (System 2). Recent studies have investigated fast and slow thinking in LLMs, focusing on system switch based on task complexity or uncertainty. Specifically, ... | https://arxiv.org/abs/2505.16315v2 |
Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, and S. S. Li. Deeps... | https://arxiv.org/abs/2505.16315v2 |
Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, Peng Li, Wei Wei, Jing Shao, Chaochao Lu, Yue Zhang, Xian- Sheng Hua, Bowen Zhou, and Yu Cheng. A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond. CoRR , abs/2503.21614, 2025. [12] Yang Sui, Yu-Neng Chuang, Gua... | https://arxiv.org/abs/2505.16315v2 |
reproduction report on slow-thinking reasoning systems. CoRR , abs/2412.09413, 2024. [28] Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. Training verifiers to solve math word pro... | https://arxiv.org/abs/2505.16315v2 |
additional second of processing and reasoning incurs a significant resource cost, which could affect efficiency and effectiveness. Your task is to prioritize speed without sacrificing essential clarity or accuracy. Provide the most direct and concise answer possible. Avoid unnecessary steps, reflections, verification, ... | https://arxiv.org/abs/2505.16315v2 |
arXiv:2505.16322v1 [cs.LG] 22 May 2025AdaSTaR : Adaptive Data Sampling for Training Self-Taught Reasoners Woosung Koh1∗, Wonbeen Oh1, Jaein Jang1, MinHyung Lee1, Hyeongjin Kim1, Ah Yeon Kim1, Joonkee Kim2, Junghyun Lee3, Taehyeon Kim2, Se-Young Yun3† 1Yonsei University,2LG AI Research,3KAIST AI reiss.koh@yonsei.ac.kr, ... | https://arxiv.org/abs/2505.16322v1 |
(RFT; Yuan et al., 2023; Singh et al., 2024), offer a promising alternative. The core idea behind STaR is to enable the LM to iteratively improve itself: the model generates CoTs, verifies the final answer against ground truth, and fine-tunes on CoTs that yield correct answers. This iterative inference, verify, and tra... | https://arxiv.org/abs/2505.16322v1 |
Direct Preference Optimization (Rafailov et al., 2023) term in its objective. To curate preference pairs, it increases CoT samples from K= 2inSTaR toK= 30 .B-STaR (Zeng et al., 2025) enhances LM exploration for more diverse reasoning, and trains a separate process reward model (Uesato et al., 2022; Lightman et al., 202... | https://arxiv.org/abs/2505.16322v1 |
presented in the original implementation (Zelikman et al., 2022). βtrises over time as we follow βt+1:= 1.2(βt)in the original implementation. However, alternative STaR -based approaches (Hosseini et al., 2024; Pang et al., 2024; Zeng et al., 2025; Lin et al., 2025; Peng et al., 2025) remove this pre-determined βt, and... | https://arxiv.org/abs/2505.16322v1 |
2024; Kawabata and Sugawara, 2024; Lee et al., 2025). We empirically observe that sampling more challenging observations leads to poorer quality CoTs. Following Wei et al. (2025) and Lee et al. (2025), we leverage the strongest available teacher model (Ho et al., 2023) ( GPT 4o ) to annotate false positives. We compare... | https://arxiv.org/abs/2505.16322v1 |
using the win statistic wi, which is computed based on model perfor- mance at ˜ti(the last iteration iwas sampled): wi≡w˜ti i:=1 KPK k=1I[yi= ˆyi], where ˆyiis from π˜ti θ(e, xi). This represents the proportion of correct answers out of KCoT samples gen- erated at iteration ˜ti. Next, we elaborate on why this is a sens... | https://arxiv.org/abs/2505.16322v1 |
2024; Li et al., 2024; Zhao et al., 2025) and is supported by data selection literature showing that combining easy and hard samples yields better outcomes than selecting only hard samples (Zheng et al., 2023; Maharana et al., 2024; Cho et al., 2025). We use the training accuracy α∈[0,1]from the current iteration tas a... | https://arxiv.org/abs/2505.16322v1 |
our computational cost metric as memory usage remains approximately constant across methods. FLOPs are computed empirically following Kaplan et al. (2020), Sardana et al. (2024). Baselines. We categorize our baselines into two groups: (1) Vanilla SFT methods: Regular SFT, SFT with 8-shot chain-of-thought prompting (SFT... | https://arxiv.org/abs/2505.16322v1 |
Most works that build on STaR choose to accumulate the model over iterations. We incorporate AdaSTaR onSTaR-Acc , asSTaR consistently performs empirically worse. Next, STaR-Full andSTaR-Acc-Full , which is an alternative approach to eliminating the CoT sampling inefficiency described in Remark 1. In -Full , the predete... | https://arxiv.org/abs/2505.16322v1 |
lowest PFLOPs to be conservative. Finally, for an intuitive visual understanding of our HieMinHeap , we provide empirical visualizations in Appendix § G. To further evaluate generality, we test AdaSTaR on datasets that perform relatively weakly on Llama 3.2 3B using different base models and sizes. Therefore, on Qwen 2... | https://arxiv.org/abs/2505.16322v1 |
of obser- vations’ trained frequency distribution is computed from iterations 1 to 2, 1 to 10, or 1 to 20 for benchmarks that converge very quickly (GSM8K), quickly (ARC-C, SV AMP), or slowly (CQA, CLadder 1.5, ANLI), respectively. Largest Acc. and lowest SD is bolded , and second is underlined . Evaluation ARC-C CQA C... | https://arxiv.org/abs/2505.16322v1 |
empirically find that the viability of self-improvement via STaR depends on the difficulty of the task relative to the strength of the base model. Therefore, as discussed in § 4.1 and Appendix F, while STaR -based approaches fail to self- improve on Llama 3.2 3B , self-improvement can be realized on the better pre-trai... | https://arxiv.org/abs/2505.16322v1 |
Berlin, Germany, August 1-7, 2015, Proceedings 25, pages 378–388. Springer, 2015. URL https://link.springer.com/chapter/10.1007/ 978-3-319-21401-6_26 . DeepSeek-AI. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learn- ing. arXiv preprint arXiv:2501.12948 , 2025. URL https://arxiv.org/abs/250... | https://arxiv.org/abs/2505.16322v1 |
Dacheng Tao. Adaptive Curriculum Learning. In Proceed- ings of the IEEE/CVF International Conference on Computer Vision (ICCV) , pages 5067–5076, October 2021. URL https://openaccess.thecvf.com/content/ICCV2021/html/Kong_ Adaptive_Curriculum_Learning_ICCV_2021_paper.html . Jaehyeok Lee, Keisuke Sakaguchi, and JinYeong ... | https://arxiv.org/abs/2505.16322v1 |
doi: 10.18653/v1/2021.naacl-main.168. URL https://aclanthology.org/2021.naacl-main.168/ . Xiangyu Peng, Congying Xia, Xinyi Yang, Caiming Xiong, Chien-Sheng Wu, and Chen Xing. Regenesis: LLMs can grow into reasoning generalists via self-improvement. In The Thirteenth International Conference on Learning Representations... | https://arxiv.org/abs/2505.16322v1 |
Zhang, Ge Li, and Zhi Jin. Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages 5878–5895, Torino, Italia, May 2024. ELRA a... | https://arxiv.org/abs/2505.16322v1 |
Curran Associates, Inc., 2022b. URL https://openreview.net/forum?id=_VjQlMeSB_J . Jerry Wei, Jason Wei, Yi Tay, Dustin Tran, Albert Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, and Tengyu Ma. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846 , 2023. URL htt... | https://arxiv.org/abs/2505.16322v1 |
https://openreview.net/forum?id=3ogIALgghF . Haizhong Zheng, Rui Liu, Fan Lai, and Atul Prakash. Coverage-centric Coreset Selection for High Pruning Rates. In The Eleventh International Conference on Learning Representations , 2023. URL https://openreview.net/forum?id=QwKvL6wC8Yi . 15 A Total Training Time Comparison F... | https://arxiv.org/abs/2505.16322v1 |
1 2 3 4 5 6 7 8 9 10 Accumulated Trained Frequency050100150200250300350400Number of Observations(a) Distribution of frequency trained of each observation iin iterations 1 to 10 in GSM8K. 0 20 40 60 80 100 Percent of [Q1] or [Q4] in Quartiles[Q1] t+1 t+2 t+3 [Q4] t+1 t+2 t+370.8 48.1 39.4 0.0 0.0 0.029.2 43.6 40.3 0.0 0... | https://arxiv.org/abs/2505.16322v1 |
is the batch size for each gradient update step. In the case that Mt> βt, some ⟨xi,ˆci,ˆyi⟩, are discarded. Such discarded samples can not be cached and use in the next iteration t+ 1because the fundamental idea of iterations is that an improved model πt+1 θis used to generate new samples. The compute and memory wastag... | https://arxiv.org/abs/2505.16322v1 |
Adam Adam Adam Adam Adam Adam Model precision bf16 bf16 bf16 bf16 bf16 bf16 Samples for self consistency 5 5 5 5 5 5 Inference decoding temperature 1.0 1.0 1.0 1.0 1.0 1.0 Evaluation decoding temperature 0 0 0 0 0 0 Rationalization (default) True True True True False False Table 3: Hyperparameters across datasets. 20 D... | https://arxiv.org/abs/2505.16322v1 |
using Llama 3.2 3B as the base model. 21 G Visualizing Empirical Heaps Last Sampled Iteration t 1 23 45 67 89 1011 1213 1415 1617 1819 2021 2223 2425 2627 2829 0 20 40 60 80 100 Percentage (%)123456789101112131415161718Iteration t (a) ARC-C 0 20 40 60 80 100 Percentage (%)12345678910111213141516171819202122232425Iterat... | https://arxiv.org/abs/2505.16322v1 |
53.0 5.5e1.2 82 .0 4e 0.05 SFT + 5-SC 66.0 0.5e0.01 67 .6 7e 1.6 61 .0 3e 0.04 STaR 82.0 17it530.6 62 .4 28it13105 .8 87 .0 15it332.8 STaR-Full 76.2 3it 93.5 43.8 12it5536.6 67 .5 36it832.9 STaR-Acc 85.4 13it383.0 62 .0 20it9298.8 87.0 13it281.3 STaR-Acc-Full 84.6 20it 533.0 61.8 8it 3751.0 87.5 24it510.6 STaR-Acc-Full... | https://arxiv.org/abs/2505.16322v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.