Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and data, making it difficult to attribute why one frontier agent outperforms another to specific research capabilities. In this work, we isolate and systematically evaluate...
Rui-Feng Yuan, Yi-Zhi Li, Ya-Xin Du et al.· arXiv.org· 0 citations
Purpose: This study examines whether domain-specific public mood is associated with stock-market dynamics and whether these relationships vary across communication domains and market conditions. It distinguishes public mood from investor sentiment and investigates whether heterogeneous sources of public communication e...
Ece Elif Adak, B. Sahin, Şaziye Betül Özateş· 0 citations
Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass. Recent parallel drafters have achieved breakthrough performance in frontier production models, but their effectiveness deteriorates as the entropy of target distributions increases due to insuffic...
Chumeng Liang, Lin-Xuan Wang, Xin-Yu Peng et al.· 0 citations
AdaGEPA is proposed, an adaptive feedback-allocation method that uses the prompt's performance and task structure to select examples for the next prompt revision, and highlights the potential of adaptive feedback allocation to improve both the effectiveness and rollout-budget efficiency of reflective prompt optimizatio...
We test whether large language models solve formally matched kinship problems equally well when relations are expressed in familiar vocabulary or by explicitly defined nonce predicates. Across 500 paired graphs, concrete accuracy exceeds arbitrary accuracy by 35.6 percentage points in local Qwen3.8-27B, 26.6 in Gemma 4...
Role-playing prompting has become a popular yet simple technique for improving LLM reasoning and output quality. However, whether it consistently boosts performance across diverse domains remains unclear, as systematic validation is lacking. To fill this gap, we run multi-model, cross-domain, and multilingual experimen...
Xing-Jie Zhuang, Jia-Long Tang, Chu-Lun Zhou et al.· 0 citations
Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based KGQA methods rely on traversing existing graph edges and become unreliable when reasoning paths are broken by missing facts. Alternatives that ask LLMs to generate missi...
Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evidence from multiple sources. Predefined memory workflows cannot adapt to these varying needs. Recent adaptive methods search or learn over memory components and their comp...
Long-context reasoning faces two complementary bottlenecks: retaining evidence across long inputs and sustaining computation across many reasoning steps. Existing approaches largely address them separately, with external memory extending access to distant evidence and latent reasoning compressing multi-step computation...
Xiao-Qiang Wang, Suyuchen Wang, Bang Liu· 1 citation
Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produces from what it discusses. We present Drift Inspector, an open-source system for measuring and exploring how a research field changes over time at the level of Atomic C...
Vsevolod Karimov, Stepan Ostarkov, Anastasia Poroshina et al.· 0 citations
Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context length. Research thus spans explicit-memory compression, sparse access, recurrent state construction, structured state dynamics, and heterogene...
Zhen-Tao Tan, Jing-Yi Shen, Yan-Bo Li et al.· arXiv.org· 0 citations
Tabular learning uses structured data to predict target outcomes. Traditionally, this process has relied on labeled data. However, large language models (LLMs) can be used to elicit domain priors based on the task description and feature semantics, thereby enabling predictions without labeled data. We propose Marginal...
Liang-Yu Teng, Yi-Chen Ding, Jing Liu et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
