text string | source string |
|---|---|
consistently brings further improvements, confirming the effectiveness of our tailored RL strategy. Tool-Use Efficiency Analysis. To validate whether Tool-Star can efficiently invoke tools during stepwise reasoning, we compare the Tool-use Accuracy TEof various TIR methods on knowledge- intensive and computation-based ... | https://arxiv.org/abs/2505.16410v1 |
TIR capabilities on top of the cold-start initialization. (3) Notably, the average reward shows signs of emergent improvement around step 10, while no clear inflection point (i.e., “aha moment”) is observed in response length. Instead, response lengths gradually stabilize, suggesting convergence toward optimized respon... | https://arxiv.org/abs/2505.16410v1 |
2025. [4]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 problems. CoRR , abs/2110.14168, 2021. 11 [5]Karl Cobbe, Vineet Kosaraju, Mohammad B... | https://arxiv.org/abs/2505.16410v1 |
Yuyang Zhou, Y . X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang ... | https://arxiv.org/abs/2505.16410v1 |
Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023 , pages 1049–1065. Association for Computational Linguistics, 2023. [22] Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Wayne Xin Zhao, Ya... | https://arxiv.org/abs/2505.16410v1 |
Zhijiang Guo, Le Song, and Cheng-Lin Liu. From system 1 to system 2: A survey of reasoning large language models. CoRR , abs/2502.17419, 2025. [37] Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step.... | https://arxiv.org/abs/2505.16410v1 |
Tur, and Heng Ji. Toolrl: Reward is all tool learning needs. arXiv preprint arXiv:2504.13958 , 2025. [46] Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, and Heng Ji. Toolrl: Reward is all tool learning needs, 2025. [47] Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong... | https://arxiv.org/abs/2505.16410v1 |
with foundation models. CoRR , abs/2312.11562, 2023. [58] Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Wayne Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, and Ji-Rong Wen. Simpledeepsearcher: Deep information seeking via web-powered reasoning trajectory synthesis. 2... | https://arxiv.org/abs/2505.16410v1 |
Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zhifang Guo, and Zhihao Fan. Qwen2 technical report. CoRR , abs/2407.10671, 2024. [71] An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xi... | https://arxiv.org/abs/2505.16410v1 |
. . . . . . . . . . . . . . . . . . . . . . . . 19 B Details of Tool-Star Framework 20 B.1 Training Algorithm of Tool-Star . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 B.2 Details of Tool Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 C Implementation Details 22 C.1 The Statistics... | https://arxiv.org/abs/2505.16410v1 |
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 E.2 Cases of Self-Critic DPO Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 F Limitations and Future Directions 27 G Broader Impacts 28 18 Table 3: The performance of Tool-Star and other baseline methods on the GAIA and HLE datasets. The ... | https://arxiv.org/abs/2505.16410v1 |
are masked. Based on this design, we conduct ablation studies on Tool-Star (Qwen2.5-3B-Instruct) with or without tool-call masking in RL training. As shown in Figure 8, removing the masking leads to a rapid collapse of the model’s reward score to -1, with persistent strategy hacking. This stands in contrast to prior fi... | https://arxiv.org/abs/2505.16410v1 |
[58] TIR Knowledge-Intensive Reasoning 0.9k WebWalker [68] Language-only Knowledge-Intensive Reasoning 3k •Search Engine: During inference, the search engine executes queries to retrieve relevant infor- mation, supporting both local and web-based retrieval modes. Inspired by DeepResearch [ 81], we adopt web search duri... | https://arxiv.org/abs/2505.16410v1 |
Table 5. We strictly adhere to all copyright and licensing terms associated with the datasets and open-source code. For the computational reasoning dataset, we use 72.4K samples aligned with Numina-MATH TIR. For knowledge-based reasoning, we include 10.6K samples from HotpotQA and 2Wiki, aligned with R1 Searcher and Re... | https://arxiv.org/abs/2505.16410v1 |
the tokens from the text-based reasoning process and tool requests are considered during loss calculation. Self-Critic DPO Training. In this phase, the learning rate is set to 5e-7 with a cosine scheduler and a 0.1 warm-up ratio. We use DeepSpeed ZeRO Stage 3 and Flash-Attention 2 for efficiency, with a global batch si... | https://arxiv.org/abs/2505.16410v1 |
ensure consistency. •Search-R1 [ 23]is a reinforcement learning method that trains a model from scratch to call the search engine during reasoning. Its overall process is similar to Search-o1 [ 31]: the model generates necessary queries during reasoning, retrieves relevant information, and inserts it into the reasoning... | https://arxiv.org/abs/2505.16410v1 |
benchmark for assessing the mathematical reasoning abilities of large language models through grade-school level word problems. In our experiments, we utilize its standard test set and report performance based on greedy decoding accuracy (maj@1). •MATH [ 18]is a dataset consisting of challenging high school-level mathe... | https://arxiv.org/abs/2505.16410v1 |
result here </result> <think> This is the reasoning process. </think> <answer> The final answer is answer here </answer>. In the last part of the answer, the final exact answer is enclosed within \boxed{} with latex format. D.2 Instructions for Code Debugger Instruction for Code Debugger You are a code expert. I need y... | https://arxiv.org/abs/2505.16410v1 |
reasoning, we conducted a case study to clearly illustrate its reasoning process. The model-generated think process are enclosed within <think> and </think> . The model-generated search queries are enclosed within <search> and </search> , and the model-generated Python codes are enclosed within <python> and </python> .... | https://arxiv.org/abs/2505.16410v1 |
4) provides preliminary evidence of the Tool-Star framework’s scalability. In future work, we aim to extend our experiments to larger models, such as 7B and 32B, to assess generalization across more complex tasks and model capacities. Outlook: Achieving reliable and robust step-by-step reasoning remains a challenging t... | https://arxiv.org/abs/2505.16410v1 |
55,840, or 56k people, for the year 2024. （***More reasoning contentare omitted here***) After the 1960 ´s, the population in the towns grew rapidly. As of January 1, 2023, the population of Greenland amounted to 56,609. The majority of the population held the Danish citizenship, as the country is an autonomous region ... | https://arxiv.org/abs/2505.16410v1 |
the first search query: </think> <search> D1NZ racing series oversteering technique </search> <result> “Drifting (motorsport)” Drifting (motorsport) Drifting is a driving technique where the driver intentionally oversteers, with loss of traction in the rear wheels or all tires, while maintaining control and driving the... | https://arxiv.org/abs/2505.16410v1 |
When Aya walks at skm/h, the total time taken is 4 hours, which includes tminutes spent in the coffee shop. Converting tminutes to hours, we gett 60. So the equation becomes: 9 s+t 60= 4 - When Aya walks at s+ 2km/h, the total time taken is 2 hours and 24 minutes, which is 2 +24 60= 2.4hours. Converting tminutes to hou... | https://arxiv.org/abs/2505.16410v1 |
So the reward score is: 1 32 Table 10: Example 1 with negative output of our self-critic reward finetuning dataset, including the question, model output, corresponding reward principle and reward score. The special symbols used in think content, Python codes, returned results and final answer highlighted with purple bo... | https://arxiv.org/abs/2505.16410v1 |
is: 0 33 Table 11: Example 2 with positive output of our self-critic reward finetuning dataset, including the question, model output, corresponding reward principle and reward score. The special symbols used in think content, Python codes, returned results and final answer highlighted with purple box ,blue box and red ... | https://arxiv.org/abs/2505.16410v1 |
the number of terms. Solving for n, we get n=an−a1 d+ 1. Substituting the values an= 9996 ,a1= 1001 , andd= 7, we get n=9996−1001 7+ 1 =8995 7+ 1 = 1285 + 1 = 1286 .</think> <python> <python> # Calculate the number of terms in the arithmetic sequence first_term = 1001 last_term = 9998 common_difference = 7 n = ((last_t... | https://arxiv.org/abs/2505.16410v1 |
others are not, the correct answer is D. </think> <answer> D </answer> Reward Principle of Output The response format is correct. The final answer is correct. The reasoning chain contains single tool usage. Reward Score of Output So the reward score is: 1 36 Table 14: Example 3 with negative output of our self-critic r... | https://arxiv.org/abs/2505.16410v1 |
now define an algorithm: The definition of a(n)is: The nearest integer to the imaginary part of the n-th nontrivial zero of the Riemann zeta function, where the zeros are listed in order of increasing positive imaginary parts. Given the input list: xlist= [50 ,51,52,53,54,55,56,57,58,59] Determine the corresponding out... | https://arxiv.org/abs/2505.16410v1 |
50th through 59th nontrivial zeros of the Riemann zeta function and round them to the nearest integers. I will use the mpmath library to perform these computations. </think> <python> import mpmath # Set high precision for accurate computation mpmath.mp.dps = 50 # Decimal places of precision # Function to get the neares... | https://arxiv.org/abs/2505.16410v1 |
arXiv:2505.16415v1 [cs.CL] 22 May 2025Attributing Response to Context: A Jensen–Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation Ruizhe Li1∗Chen Chen2Yuchen Hu2Yanjun Gao4Xi Wang5Emine Yilmaz3 1University of Aberdeen2Nanyang Technological University3University College... | https://arxiv.org/abs/2505.16415v1 |
identify context segments crucial for grounding model responses. However, Cohen-Wang et al [ 5] still need hundreds of RAG model’s forward calls to collect proba- bility ablation samples for the linear surrogate model training. We propose a novel inference-time Jensen– Shannon Divergence driven method to Attribute Resp... | https://arxiv.org/abs/2505.16415v1 |
to [ 5,3] and corroborative methods above, our ARC-JSD method eliminates the need for any additional fine-tuning or surrogate modelling, and it can be directly integrated into any existing RAG-based LLMs. 2 Mechanistic analysis for RAG. Existing mechanistic studies mainly focus on the next token generation task to anal... | https://arxiv.org/abs/2505.16415v1 |
token prediction probability distribution is computed as: PLM(tT+1|t1:T) =Softmax WUσ(xL T) , where WU∈Rd×|V|is the unembedding matrix, and σ(·)denotes pre-unembedding layer normalization. The attention module, including multiple attention heads, primarily modifies each token’s residual stream representation by atten... | https://arxiv.org/abs/2505.16415v1 |
about 425 feet (130m) long and 57 feet (17.4m) beam.[3]Query (Q) Who founded the Burntisland Shipbuilding Company?Context by ablating the second sentence CABLATE(c2)Context by ablating the third sentence CABLATE(c3) .generate()Generated Response (R)Amos and Wilfrid Ayre founded the Burntisland Shipbuilding Compony in 1... | https://arxiv.org/abs/2505.16415v1 |
the assumption about the significant impact of removing critical context segments: ci= arg max ci∈C {JSD(ci)}|C| i=1 (2) 4.2 Evaluation of Context Attribution Accuracy Table 1: The size of three benchmarks randomly sampled from their develop- ment dataset is up to 1000, where the av- erage word numbers and sentence n... | https://arxiv.org/abs/2505.16415v1 |
of RAG LLMs: (a)For each attention head or MLP output at each layer, we can calculate the probability distribution of the same response Rconditioned on the same query Qwith full context Cand ablated context CABLATE (ctop-1)by removing the top relevant context sentence based on § 4.1; (b)We can further locate top- Nrele... | https://arxiv.org/abs/2505.16415v1 |
MLPs using JSD-based metric from the § 5.1, we also know that semantic information of context attribution from attentions and MLPs will be added back to the residual stream from each layer based on the autoregressive language model’s architecture from the § 3 [ 7,13]. Based on such properties, we can verify whether the... | https://arxiv.org/abs/2505.16415v1 |
correlation of both metrics and further verify the effectiveness of our proposed ARC-JSD metric in the § 4.1 and § 5.1. Given {JSDℓ MLP}L ℓ=0and{∆ℓ,MLP}L ℓ=0via the JSD-based and Semantic-gain-based metrics, we first define an average-ranking fusion, called consensus S(+), to fuse both JSD and semantic gain views, whic... | https://arxiv.org/abs/2505.16415v1 |
the decoded token of the corresponding xℓ,mid i orxℓ,post i via Logit Lens. feathery antennae, and elongated mouthparts ”. When we compare the heatmap between xℓ,post i and xℓ,mid i in Figure 4 from Layer 20 to Layer 27 (See Appendix J for the whole heatmap), we can find that the probability of correct token is increas... | https://arxiv.org/abs/2505.16415v1 |
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 8493–8502, 2022. [7]Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, et al. A mathematical framework for transfo... | https://arxiv.org/abs/2505.16415v1 |
Locally-attributable grounded text generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 3309–3344, 2024. [23] Maojia Song, Shang Hong Sim, Rishabh Bhardwaj, Hai Leong Chieu, Navonil Majumder, and Soujanya Poria. Measuring and enhancing tr... | https://arxiv.org/abs/2505.16415v1 |
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages 6237–6251, 2024. [37] Xiang Yue, Boshi Wang, Ziru Chen, Kai Zhang, Yu Su, and Huan Sun. Automatic evaluation of attribution by large language models. In Findings of the ... | https://arxiv.org/abs/2505.16415v1 |
σ(·)and the unembedding matrix WU∈Rd×|V|produce the next-token distribution PLM(tT+1|t1:T) = softmax WUσ(xL T) . (14) Each layer contains Hattention heads, each factorised into QK andOV circuits operating with weight matrices Wℓ,h Q, Wℓ,h K, Wℓ,h V, Wℓ,h O∈Rd×d. The QK circuit establishes the attention pattern Aℓ,h∈R... | https://arxiv.org/abs/2505.16415v1 |
each example includes the query, generated responses and located top-1 sentence from the context. 14 Figure 5: Computational efficiency comparison between our ARC-JSD and Contextcite ( n= 256 calls) across all datasets and RAG models. Each bar represents the average seconds per sample for ARC-JSD and Contextcite with d... | https://arxiv.org/abs/2505.16415v1 |
layers. The deeper colour indicates larger JSD scores. 17 MLPQwen2-1.5B-ITonMuSiQueAttentionFigure 7: The average JSD score of attention heads and MLP of Qwen2-1.5B-IT on MuSiQue dataset across all layers. The deeper colour indicates larger JSD scores. Attention MLPGemma2-2B-ITonTyDiQA Figure 8: The average JSD score o... | https://arxiv.org/abs/2505.16415v1 |
arXiv:2505.16418v1 [cs.CL] 22 May 2025Exploring the Relationship Between Diversity and Quality in Ad Text Generation Yoichi Aoki1,2, Soichiro Murakami3, Ukyo Honda3, Akihiko Kato3 1Tohoku University,2RIKEN,3CyberAgent youichi.aoki.p2@dc.tohoku.ac.jp, {murakami_soichiro,honda_ukyo,kato_akihiko}@cyberagent.co.jp, Abstrac... | https://arxiv.org/abs/2505.16418v1 |
on the number of few-shot examples and outputs. These findings highlight the need for the careful use of diversity-enhancing methods in ad text generation. Moreover, we also provide promising directions for enhancing diver- sity while maintaining ad quality by combining the outputs of a set of different models. 2 Probl... | https://arxiv.org/abs/2505.16418v1 |
calm3’s results and those of the other models in the Appendix B. 3.1 Diversity vs. Ad Quality Across Diversity-Enhancing Methods As shown in Figure 2, we found a trade-off be- tween diversity and ad quality, with each value representing the average across the dataset. This suggests that the nature of ad generation diff... | https://arxiv.org/abs/2505.16418v1 |
ad quality when varying the parameter of diversity-enhancing methods. Diversity, Ad Performance, Ad Consistency, and Ad Acceptabil- ity are denoted as Div., Per., Con., and Accept., respec- tively. The same notation is used in the following ta- bles. We varied the p-value (P) and temperature (T) for sampling, the beam ... | https://arxiv.org/abs/2505.16418v1 |
improved diversity but worsened quality compared with one-at-once, in- dicating a trade-off. This diversity improvement could be because all-at-once can output ad text by reviewing previous outputs. 3.6 Diverse Outputs via Multiple Models We compared generating five texts with a single model to generating one text with... | https://arxiv.org/abs/2505.16418v1 |
Diverse search ad genera- tion and real-time customization. In Proceedings of the The 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Sys- tem Demonstrations, Abu Dhabi, UAE, December 7- 11, 2022 , pages 191–199. Association for Computa- tional Linguistics. Alex Graves. 2012. Sequence ... | https://arxiv.org/abs/2505.16418v1 |
(Vol- ume 1: Long Papers), ACL 2024, Bangkok, Thai- land, August 11-16, 2024 , pages 955–972. Associa- tion for Computational Linguistics. Soichiro Murakami, Sho Hoshino, and Peinan Zhang. 2023. Natural language generation for advertising: A survey. CoRR , abs/2306.12719. Soichiro Murakami, Peinan Zhang, Hidetaka Kami-... | https://arxiv.org/abs/2505.16418v1 |
formed inference once and output the top five candidates obtained. The parameters for each diversity-enhancing method used in the experi- ment are listed in Table 6. Note that in § 3.4, the beam search and diverse beam search had a fixed beam width of 15. We used NVIDIA A100 (80GB) GPUs for the generation. method param... | https://arxiv.org/abs/2505.16418v1 |
side jobs # 吉祥寺の副業でお金儲け Input: Corporate-focused [Immediate Strength Recruitment] # 法人向け【即戦力採用】 Output: Seeking immediate strength! Corporate recruitment # 即戦力求む！法人採用 Input: Ad content Table 7: Model input for ad text generation. For visibility, Japanese prompt is translated into English. On the right side of each inpu... | https://arxiv.org/abs/2505.16418v1 |
# 法人向けの人材即戦力 Output4: Corporate immediate impact hiring # 法人用即戦力採用 Output5: Immediate impact hiring for companies # 企業向け即戦力採用 Input: Ad content Table 8: Model input for ad text generation in an all-at-once setting. the diversity-enhancing methods in an all-at-once setting. The results are presented in Figure 15. The re... | https://arxiv.org/abs/2505.16418v1 |
Beam Searchdiverse beam searchDMBR KMBR Figure 8: Diversity and ad quality of sampling when varying the instruction Please select the more **attractive** ad text. If there is no difference in impression between the two ad texts, please click "No Difference". 【Evaluation Criteria 】 - Do you want to click on it? - Is it ... | https://arxiv.org/abs/2505.16418v1 |
arXiv:2505.16421v1 [cs.CL] 22 May 2025WEBAGENT -R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning Zhepei Wei†*, Wenlin Yao‡, Yao Liu‡, Weizhi Zhang‡, Qin Lu‡, Liang Qiu‡ Changlong Yu‡, Puyang Xu‡, Chao Zhang§, Bing Yin‡, Hyokun Yun‡, Lihong Li‡ †University of Virginia‡Amazon§Georgia Institute of ... | https://arxiv.org/abs/2505.16421v1 |
Pan et al., 2024; Qi et al., 2025), which break the end-to-end interaction between the web agent and environment, and introduce additional complexi- ties such as trajectory filtering (Bai et al., 2024), outcome reward model training (Qi et al., 2025), or iterative optimization procedures (Zhou et al., 2024b). These con... | https://arxiv.org/abs/2505.16421v1 |
web agent training. 3B 8B 32B Unknown Model Size01020304050Success Rate (%) Qwen2.5-3BLlama3.1-8BQwen2.5-32BQwQ-32B GPT-4oGPT-4o-TurboOpenAI-o3 OpenAI-o4-mini Filtered BC (Llama3.1-8B)AWR (Llama3.1-8B)DigiRL (Llama3.1-8B)WebRL (Llama3.1-8B) SFT (Qwen2.5-3B) SFT (Llama3.1-8B)WebAgent-R1 (Qwen2.5-3B)WebAgent-R1 (Llama3.1... | https://arxiv.org/abs/2505.16421v1 |
page screenshots as additional vi- sual inputs, whereas our work focuses solely on text-based decision-making over HTML. Other ef- forts, such as Yang et al. (2025b), explore opti-mizing the action space or prompt design without model fine-tuning. These directions are orthogonal to our investigated problem and can be c... | https://arxiv.org/abs/2505.16421v1 |
1, a1, s′ 2, a2, . . . , s t), where each s′ iis a simplified template ( e.g., “Simplified HTML” ) representing prior observa- tions. When the agent executes an action atand re- ceives a new observation st+1, the updated history becomes ht+1= (s′ 1, a1, s′ 2, a2, . . . , s′ t, at, st+1), where stis replaced by its simp... | https://arxiv.org/abs/2505.16421v1 |
2025) 63.2 46.7 54.3 36.7 31.1 42.4 WEBAGENT -R1 47.4 56.7 57.1 23.1 44.4 44.8 Reward Design We use the default rule-based reward functions in the web environment, which assign binary rewards ( r=1for success, r=0other- wise) based on task-specific criteria ( e.g., reaching a target page). This eliminates the need for ... | https://arxiv.org/abs/2505.16421v1 |
pared to general-purpose LLMs, models equipped with explicit thinking capabilities perform signifi- cantly better on web tasks, likely due to their ability to decompose high-level goals and explicitly lay out dynamic changes in the web interface. This gap underscores the importance of thinking in web environments, whic... | https://arxiv.org/abs/2505.16421v1 |
Response Length R1-Zero R1-CoT R105101520Number of Interactions17 9 912 10 8Before RL After RL (c) Number of Interactions Figure 4: Ablation study on RL initialization policy by comparing WEBAGENT -R1 (R1) with two variants: WEBAGENT -R1-Z ERO (R1-Zero), initialized from an off-the-shelf model without SFT, and WEBAGENT... | https://arxiv.org/abs/2505.16421v1 |
LLMs as web agents. As shown in Table 3, using the thinking format significantly improves task success rates across models, partic- ularly for stronger ones ( e.g., o4-mini improves from 15.9% to 36.9%). Interestingly, while the average single-turn response length remains simi- lar (e.g., 139→142 tokens for Qwen2.5-3B)... | https://arxiv.org/abs/2505.16421v1 |
on single-turn tasks such as math problems (Shao et al., 2024), with limited exploration in multi-turn settings (Zhou et al., 2024b, 2025). Recent efforts have made some progress in this direction, such as training LLM agents to repeatedly use search en- gines (Jin et al., 2025; Sun et al., 2025; Chen et al., 2025; Son... | https://arxiv.org/abs/2505.16421v1 |
sentations . Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems , 36:28091–28114. Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Man- dlekar, Yuncong Yang, Haoyi Zhu, Andrew Ta... | https://arxiv.org/abs/2505.16421v1 |
IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages 14445–14454. Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Lim, Po-Yu Huang, Graham Neu- big, Shuyan Zhou, Russ Salakhutdinov, and Daniel Fried. 2024. Visualwebarena: Evaluating multimodal agents on realistic visual web tasks. In Procee... | https://arxiv.org/abs/2505.16421v1 |
Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, and 1 others. 2021. WebGPT: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 . Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Wenqi Fan, Xiao-yong Wei, Shanru ... | https://arxiv.org/abs/2505.16421v1 |
Mod- eling . Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji- Rong Wen. 2025. R1-searcher: Incentivizing the search capability in LLMs via reinforcement learning. arXiv preprint arXiv:2503.05592 .Hao Sun, Zile Qiao, Jiayan Guo, Xuanbo Fan, Yingyan Hou, Yong Jiang, Peng... | https://arxiv.org/abs/2505.16421v1 |
Zhang, Zijian Ma, Yunpu Ma, Zhen Han, Yu Wu, and V olker Tresp. 2025. Webpilot: A versatile and autonomous multi-agent system for web task execu- tion with strategic exploration. In Proceedings of the AAAI Conference on Artificial Intelligence , vol- ume 39, pages 23378–23386. Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan ... | https://arxiv.org/abs/2505.16421v1 |
a final message. •Go Backward / Go Forward : navigates back- ward or forward in the browser history.Rule-based Metrics In real-world web tasks, there are typically no closed-form solutions, and multiple trajectories may lead to successful task completion. Therefore, we evaluate agents solely based on whether the final ... | https://arxiv.org/abs/2505.16421v1 |
which is critical for accessing sales data. The dashboard’s main content shows a table with a product (“Sprite Yoga Strap 6 foot”) and quantity (6), but this appears to be static local sales data rather than a report. Since the user needs a specific monthly ranking, the Reports section is the logical path to business i... | https://arxiv.org/abs/2505.16421v1 |
14 Table 5: Prompt used for long-CoT data augmentation, with example fill-ins for the fields user intent ,action history , current observation ,next action , and remarks , all of which are available in the original behavior cloning data. The full HTML content in current observation is omitted for clarity. Long-CoT Data... | https://arxiv.org/abs/2505.16421v1 |
optional. Only for "Click", "Right Click", "Type", "Search", "Select Dropdown Option", and "Hover". Should be specific element id in the HTML. Returns: None. The webpage will be updated after executing the action. """ def exit(message): """Ending the browsing process if the assistant think it has fulfilled the goal. Ar... | https://arxiv.org/abs/2505.16421v1 |
now listed by descending price.")Step 1Step 2Step 3 Step 4Step 5Step 6 Figure 8: A real-world example of a successful trajectory generated by WEBAGENT -R1on the Shopping task: “List products from living room furniture category by descending price” . do(action=“Click”, element=“17”)do(action=“Click”, element=“21”)do(act... | https://arxiv.org/abs/2505.16421v1 |
arXiv:2505.16425v1 [cs.CL] 22 May 2025I2G: Generating Instructional Illustrations via Text-Conditioned Diffusion Jing Bi1, Pinxin Liu1, Ali Vosoughi1, Jiarui Wu1, Jinxi He1,Chenliang Xu1 1University of Rochester Abstract The effective communication of procedural knowledge remains a significant challenge in natural lang... | https://arxiv.org/abs/2505.16425v1 |
by linking visual demonstrations with textual explana- tions. These videos are not only beneficial for hu- mans, but also hold promise for machine learning, as they provide clear visual demonstrations of intri- cate tasks and detailed human-object interactions across various domains. These challenges intersect with cor... | https://arxiv.org/abs/2505.16425v1 |
Based on these hu- man evaluations, we then leveraged caption gener- ation and text similarity models that demonstrated high alignment with human judgments. These mod- els were adapted to refine our evaluation frame- work, ensuring that it not only measures photore- alism but also accurately reflects the instructional ... | https://arxiv.org/abs/2505.16425v1 |
utilizing narra- tions to contextually ground procedural steps (Han et al., 2022), enhancing performance across tasks. New benchmarks such as InstructionBench (Wei et al., 2025) explicitly evaluate question-answering over instructional videos, while Pivot pre-training exploits task hierarchies for more data-efficient r... | https://arxiv.org/abs/2505.16425v1 |
from image descrip- tion to task-specific analysis for reasoning the Text2Image generation quality. Concept cover- age (Chen et al., 2024b) calculated based on Vi- sual Question Answering semantic entropy is fur- ther proposed for aestheticism and defects qual- ification of generations. CIGEval frames GPT- 4-based visi... | https://arxiv.org/abs/2505.16425v1 |
A naive approach assumes each videpends only on (g, si): p v1, . . . , v n|g,S ≈nY i=1p vi|g, si , but often fails to maintain coherence across mul- tiple steps (see Figure 1). Although a fully joint model (Menon et al., 2023) better captures global context, it is fixed in step count and grows com- putationally exp... | https://arxiv.org/abs/2505.16425v1 |
iteratively ascend the gradient of J(θ), passing reward signals backward through each diffusion step. Over multiple epochs, the model aligns gen- erated visuals more tightly with textual goals/steps. By decoupling text generation from our image dif- fuser, we can leverage large language models di- rectly, focusing on r... | https://arxiv.org/abs/2505.16425v1 |
on goals and steps. However, our results re- veal that evaluators often struggled to identify clear connections between the goal texts and the visual content. This issue may arise because the goal texts tend to provide contextual rather than explicit visual references. Moreover, although evaluators were instructed to a... | https://arxiv.org/abs/2505.16425v1 |
(KL) divergence and the Chi-square test as metrics to quantify this discrepancy. This ap- proach addresses shortcomings observed in previ- ously proposed metrics, enhancing the accuracy of text-image alignment evaluations to better align with human preferences. We choose the below baseline model: Stable Diffusion 1.5 (... | https://arxiv.org/abs/2505.16425v1 |
text-conditioned dif- fusion framework that decomposes instructional content into goals and step-by-step instructions. Our method leverages a large language model for textual representation, combined with a feedback mechanism for image-text alignment, to generate coherent illustrations of procedural activities. The exp... | https://arxiv.org/abs/2505.16425v1 |
arXiv:2309.15807. Hanze Dong, Wei Xiong, Deepanshu Goyal, Yihan Zhang, Winnie Chow, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, and Tong Zhang. 2023. Raft: Reward ranked finetuning for generative foundation model alignment. Preprint , arXiv:2304.06767. Ying Fan, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, C... | https://arxiv.org/abs/2505.16425v1 |
Lucas Smaira, Ivan Laptev, Josef Sivic, and Andrew Zisserman. 2020. End-to-end learning of visual representa- tions from uncurated instructional videos. Preprint , arXiv:1912.06430. Rohith Peddi, Shivvrat Arya, Bharath Challa, Likhitha Pallapothula, Akshay Vyas, Jikai Wang, Qifan Zhang, Vasundhara Komaragiri, Eric Raga... | https://arxiv.org/abs/2505.16425v1 |
2023. Hu- man preference score v2: A solid benchmark for eval- uating human preferences of text-to-image synthesis. Preprint , arXiv:2306.09341. Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image ... | https://arxiv.org/abs/2505.16425v1 |
surface has some charred spots. Step7: Serve hot with curtido (a spicy cabbage slaw) and tomato salsa. Goal: Make Kolaches (Czech Pastries) Step1: Dissolve 1 packet of active dry yeast in 1/4 cup of warm water with a teaspoon of sugar. Let it sit until it becomes frothy, about 5-10 minutes. Step2: In a large bowl, mix ... | https://arxiv.org/abs/2505.16425v1 |
this visual <image>." Choice15: "In a nutshell, what can you say about this picture <image>?" Choice16: "What’s the main subject in the im- age <image>?" Choice17: "Describe the main features of the image <image>." Choice18: "What is depicted in this photograph <image>?" Choice19: "Give me a short description of the pi... | https://arxiv.org/abs/2505.16425v1 |
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems Song Jin1*, Juntian Zhang1*, Yuhan Liu1†, Xun Zhang2,Yufei Zhang2,Guojun Yin2,Fei Jiang2,Wei Lin2,Rui Yan1,3† 1Gaoling School of Artificial Intelligence, Renmin University of China,2Meituan,3Wuhan University jinsong... | https://arxiv.org/abs/2505.16429v1 |
Hosanagar, 2021; Cui et al., 2012; Li et al., 2019) has already demonstrated the sig- nificant impact of these dynamic item attributes on user decision-making. This reciprocal relationship, where user actions reshape the environment and, in turn, influence future user decisions, is crucial for realistic simulation. To ... | https://arxiv.org/abs/2505.16429v1 |
recommendation scenarios. 2.2 Recommendation Simulation Recommendation simulators have emerged as a cor- nerstone in recommender systems research (Afsar et al., 2023; Yang et al., 2021; Luo et al., 2022; Liu et al., 2025), offering a cost-effective alternative to online testing and addressing persistent chal- lenges su... | https://arxiv.org/abs/2505.16429v1 |
and inferred profile. Objective Profile Building on the statistical met- ricsTact,Tconf, and Tconsproposed by Zhang et al. (2024), we further introduce a set of novel in- dicators aimed at enhancing the realism of userobjective profile. We conducted a systematic analysis of product categories within user inter- action ... | https://arxiv.org/abs/2505.16429v1 |
a reply for the review … I will make a review for … The experience was … Item profiles User Profile like dislike review Objective Subjective Inferred Figure 1: The overall framework of RecInter . The User Agent, equipped with user profile, memory module and action module, interacts with the platform by taking actions t... | https://arxiv.org/abs/2505.16429v1 |
Action Module We use a “think-then-act” approach, similar to chain-of-thought reasoning, enables simulated users to behave more similarly to real users, fol- lowing Yang et al. (2024). Inspired by real-world recommendation platforms, we designed a rich set of user actions that more closely reflect authentic interaction... | https://arxiv.org/abs/2505.16429v1 |
Human Filter: Involves manual verification to further ensure data quality. Following this pipeline, we curated a high- quality dataset comprising 5,295 CoT enhanced samples. We then fine-tuned the Qwen-2.5-7B- Instruct model, resulting in the base model that achieved the best simulation performance. The fine-tuning set... | https://arxiv.org/abs/2505.16429v1 |
agents. For real users, we identified the top-10 most popular items from the GoogleLocal dataset and computed their frequency distributions. Sim- ilarly, for the simulated agents, we analyzed the top-10 most frequently interacted items based on the simulation results. As shown in Figure 11, five out of the top six most... | https://arxiv.org/abs/2505.16429v1 |
in likes, sales, and re- views for McDonald’s at that point, which likely influenced agents to favor McDonald’s more fre- quently. In contrast, the difference between the two simulations for Denny’s was relatively minor. This suggests that Denny’s had insufficient attention in the early stages of the simulation, thereb... | https://arxiv.org/abs/2505.16429v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.