Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.17898v1 Announce Type: cross Abstract: Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predo...
arXiv:2610.17734v1 Announce Type: cross Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent s...
arXiv:2610.16412v1 Announce Type: new Abstract: As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summariz...
arXiv:2610.16511v1 Announce Type: new Abstract: Pattern mining is a valuable tool for exploratory data analysis, but identifying relevant patterns for a specific user is challenging. Various interest...
arXiv:2610.17590v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to t...
arXiv:2610.17596v1 Announce Type: cross Abstract: Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly...
arXiv:2610.16555v1 Announce Type: new Abstract: We introduce $qt$Bench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explai...
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central sa...
arXiv:2610.18204v1 Announce Type: cross Abstract: Connection-tableau provers typically construct closed tableaux by backtracking search. This gives lightweight proof procedures, but their low-memory...
arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a class...
arXiv:2610.16480v1 Announce Type: new Abstract: Determining crystal structures from powder X-ray diffraction (PXRD) would enable routine characterization of newly synthesized materials, including tho...
arXiv:2610.20431v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their own experimental experience. Scie...
arXiv:2610.16049v1 Announce Type: cross Abstract: Existing audio deepfake detection (ADD) methods frequently exhibit limited generalization, as fixed bottleneck architectures fail to adapt to the het...
arXiv:2610.20472v1 Announce Type: new Abstract: Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute...
arXiv:2610.16911v1 Announce Type: new Abstract: Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the im...
arXiv:2610.16545v1 Announce Type: cross Abstract: Feature caching has become a mainstream training-free strategy for accelerating video diffusion models by reusing intermediate outputs across denoisi...
arXiv:2610.16977v1 Announce Type: cross Abstract: Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depend...
arXiv:2610.17331v1 Announce Type: new Abstract: General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. Th...
arXiv:2610.17659v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, th...
arXiv:2610.18025v1 Announce Type: new Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gathe...