Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source. Meanwhile, existing benchmarks for scientific document retrieval, such as ArXivQA and ViDoRe, treat documents as images of pages, implicitly favoring such represe...
Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh et al.· 0 citations
It is found that external rewards drive most of the accuracy gains, while preserving more coherent reasoning when rewarded for reasoning tokens, while preserving more coherent reasoning when rewarded for reasoning tokens through internal attention rewards.
There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Ye...
Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS, which evaluates wh...
Sangyeon Yoon, SunKyoung Kim, Hyesoo Hong et al.· arXiv.org· 8 citations· ⚡2
Reach audiences
Advertise in front of researchers, engineers, and readers.
Draft-Thinking is proposed, a lightweight adaptation framework that learns a compact, self-contained working derivation that directly supports the final answer in a long chain-of-thought reasoning model.
Jie Cao, Tianwei Lin, Zhen-Xuan Fan et al.· arXiv.org· 3 citations· ⚡1
Crafting effective reward signals remains a central challenge in reinforcement learning (RL) for complex reasoning. Existing methods for automated reward optimization search with a fixed proposer which never learns from its costly trials. We present Dual-Evolving Reinforcement Learning (DERL), a dual-training framework...
Sitao Cheng, Tianle Li, Xuhan Huang et al.· 0 citations
Automatic prompt generation plays a crucial role in enabling general-purpose multi-agent systems to perform diverse tasks autonomously. Existing methods typically evaluate prompts based on their immediate task performance, overlooking the intrinsic qualities that determine their reliability. This outcome-centric view n...
Ke Chen, Xucheng Yu, Yufei Zhou et al.· 0 citations
Executing long-horizon tool invocations in real-world environments is severely challenged by dynamic user intent noise. Existing methods attempt robustness via implicit history scanning or text compression, yet predominantly assume perfect instructions in simplistic scenarios. Inevitably, under fluctuating contexts, ob...
Dingwei Zhu, Jiahan Li, Chengjun Pan et al.· 0 citations
Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user interaction data, limiting their applicability in privacy-conscious settings....
Fangzhou Lin, Zilin Dai, Shuo Xing et al.· 0 citations
Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy constraints. Clinical narratives are dense with ambiguous acronyms, misinterpretation these abbreviations can precipitate severe outcomes like life-threatening medication errors...
Manjushree B. Aithal, Ph. D., Alexander Kotz et al.· 0 citations
The results provide significant, multi-perspective evidence that social effects of data could be a causal driver of LLM capability decay in continual pre-training, thereby motivating routine"cognitive health checks" for deployed and evolving LLMs.
Shuo Xing, Junyuan Hong, Yi-Fan Wang et al.· arXiv.org· 3 citations
Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, even opposite, effects across regulatory regimes, market conditions, time periods, or populations. This poses a challenge for large language models (LLMs) in decision-support role...
Donggyu Lee, Hyeok Yun, Meeyoung Cha et al.· 0 citations
