Tootfinder

Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
Huifeng Lin, Gang Su, Jintao Liang, You Wu, Rui Zhao, Ziyue Li
https://arxiv.org/abs/2509.04820

Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-$k$ strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence …

Ich habe neulich die erste KI-generierte Absage auf eine Initiativbewerbung erhalten.
Woran ich es merke? Zuerst an den Superlativen („Ihre herausragenden Fähigkeiten“) und an der Passgenauigkeit im Hinblick auf mein Anschreiben.
Ich hatte auch schon menschliche Absagen, die in eine ähnliche Richtung gingen, die aber deutlich echter (und ehrlicher) klangen, weil sie nicht so verschnörkelt und „drüber“ waren.
Ob sich die Unternehmen mit so etwas einen Gefallen tun?

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
Anushka Yadav, Isha Nalawade, Srujana Pillarichety, Yashwanth Babu, Reshmi Ghosh, Samyadeep Basu, Wenlong Zhao, Ali Nasaeh, Sriram Balasubramanian, Soundararajan Srinivasan
https://arxiv.org/abs/2508.04699

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
The emergence of reasoning models and their integration into practical AI chat bots has led to breakthroughs in solving advanced math, deep search, and extractive question answering problems that requires a complex and multi-step thought process. Yet, a complete understanding of why these models hallucinate more than general purpose language models is missing. In this investigative study, we systematicallyexplore reasoning failures of contemporary language models on multi-hop question answering…

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling
Xinlei Yu, Zhangquan Chen, Yudong Zhang, Shilin Lu, Ruolin Shen, Jiangning Zhang, Xiaobin Hu, Yanwei Fu, Shuicheng Yan
https://arxiv.org/abs/2508.03404

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling
Existing vision-language models (VLMs), whether generalists or specialists, remain constrained by their parameter scale, lack robust self-correction capabilities, and underperform in tasks involving long visual contexts and complex reasoning, resulting in suboptimal performance on document-based tasks. To address this, we propose MACT, a Multi-Agent Collaboration framework with Test-Time scaling, tailored for visual document understanding and visual question answering (VQA). It comprises four d…

The Flat Cover Conjecture for Monoid Acts
Sean Cox
https://arxiv.org/abs/2507.04155 https://arxiv.org/pdf/2507.04155

The Flat Cover Conjecture for Monoid Acts
We prove that the Flat Cover Conjecture holds for the category of (right) acts over any right-reversible monoid $S$, provided that the flat $S$-acts are closed under stable Rees extensions. The argument shows that the class $\mathcal{F}$-Mono ($S$-act monomorphisms with flat Rees quotient) is cofibrantly generated in such categories, answering a question of Bailey and Renshaw. But cofibrant generation of $\mathcal{SF}$-Mono ($S$-act monomorphisms with \emph{strongly} flat Rees quotient) appears…

The canonical form, scissors congruence and adjoint degrees of polytopes
Tom Baumbach, Ansgar Freyer, Julian Weigert, Martin Winter
https://arxiv.org/abs/2508.04275 https://

The canonical form, scissors congruence and adjoint degrees of polytopes
We study the canonical form $Ω$ as a valuation in the context of scissors congruence for polytopes. We identify the degree of its numerator - the adjoint polynomial $\operatorname{adj}_P$ - as an important invariant in this context. More precisely, for a polytope $P$ we define the degree drop that measures how much smaller than expected the degree of the adjoint polynomial of $P$ is. We show that this drop behaves well under various operations, such as decompositions, restrictions to faces, pr…

Anchoring and Alignment: Data Factors in Part-to-Whole Visualization
Connor Bailey, Michael Gleicher
https://arxiv.org/abs/2508.01881 https://arxiv.org/pdf…

Anchoring and Alignment: Data Factors in Part-to-Whole Visualization
We explore the effects of data and design considerations through the example case of part-to-whole data relationships. Standard part-to-whole representations like pie charts and stacked bar charts make the relationships of parts to the whole explicit. Value estimation in these charts benefits from two perceptual mechanisms: anchoring, where the value is close to a reference value with an easily recognized shape, and alignment where the beginning or end of the shape is aligned with a marker. In …

Do Robots Really Need Anthropomorphic Hands?
Alexander Fabisch, Wadhah Zai El Amri, Chandandeep Singh, Nicol\'as Navarro-Guerrero
https://arxiv.org/abs/2508.05415 https://…

Do Robots Really Need Anthropomorphic Hands?
Human manipulation skills represent a pinnacle of their voluntary motor functions, requiring the coordination of many degrees of freedom and processing of high-dimensional sensor input to achieve such a high level of dexterity. Thus, we set out to answer whether the human hand, with its associated biomechanical properties, sensors, and control mechanisms, is an ideal that we should strive for in robotics-do we really need anthropomorphic robotic hands? This survey can help practitioners to ma…

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Shudong Liu, Hongwei Liu, Junnan Liu, Linchen Xiao, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen
https://arxiv.org/abs/2508.03686

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward model to guide LLM optimization. Most evaluation frameworks rely on regularized matching or employ general LLMs for answer verification, which demands extensive, repetitive customization for regex rules or evaluation prompts. Two fundamental limitations persist in current methodologies: 1) the absence of comprehensive …

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
Chenglei Shen, Zhongxiang Sun, Teng Shi, Xiao Zhang, Jun Xu
https://arxiv.org/abs/2508.04530

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness. Existing representation editing methods, by naively injecting style signals, overlook this collateral impact and frequently contaminate the model's core truthfulness representations, resulting in reduced answer correctness. We term this phenomenon stylization-…