Explore tools, prompts, skills, news and resources related to arXiv 第3页.
Latest articles, prompts, use cases and editorial content about arXiv 第3页
TaskFrame is a hierarchical planner-controller framework that pairs a vision-language task planner with a causal Transformer controller that emits keyboard and mouse actions at every game step. The planner decomposes a h...
The paper analyzes advantage estimation in GRPO and factors it into sample-level baselining and token-level credit assignment, noting that existing estimators typically handle only one stage. TACE replaces linear standar...
Researchers used 2.71 million reactions to test whether retrieving reaction precedents can compensate for gaps in task-specific training coverage. With model parameters fixed, expanding only the retrieval corpus raised m...
EnvOS is a research framework that checks whether mid-task environment changes execute correctly, tasks remain solvable, and graders distinguish correct from incorrect behavior, then independently rechecks verdicts again...
A new arXiv paper introduces EpiAgent, a framework that gives LLM-based agents an explicit, learnable epistemic layer holding beliefs about other agents' private information. The agent's policy is split into tw...
Researchers present Bridge-LP, a cross-modal framework that unifies graph and language representations for link prediction on text-attributed graphs. The design combines textual-proximity jumping connections, compressed...
The authors extend the Single Location Regression framework from Marion et al. [2025] to 2D structured data in order to study sparse-information settings where a target depends on only a small number of tokens. They form...
The paper addresses a structural weakness in fixed multi-agent workflows, where evidence gathered by one agent may never reach the agent that needs it, producing an information gap and an incorrect answer. SPLICE runs th...
EventSeeColor combines event-reconstructed grayscale images with aligned event data to guide a diffusion-based colorizer. The method uses semantic context, region-balanced chroma supervision and local RGB refinement to i...
The paper proposes a framework that refines natural-language cloud intents, dynamically detects conflicts, and structures the result into a provider-independent TOSCA template. Candidate service offers are then retrieved...
FARE is a retrieval-augmentation method for short-term retail demand forecasting, where target weeks often combine promotion and calendar factors that have few exact historical precedents. It ranks historical weeks separ...
DynaRev introduces 181 tasks that evaluate how web agents respond when users revise requirements during execution, measuring correctness, responsiveness and efficiency. Evaluations across five models show that agents oft...
A new arXiv paper addresses offline goal-conditioned reinforcement learning in stochastic long-horizon settings, where compounding value-estimation errors make reliable goal reaching difficult. The authors identify a fai...
This arXiv paper introduces RACE, a framework that co-evolves a reinforcement-learning policy and the rubric used to score open-ended responses. At the group level, per-rollout-group signal routing classifies groups as i...
The paper proposes Domain-Specialized Upcycling (DS-Upcycling), which expands a dense Transformer layer with additional experts and a router rather than attaching per-domain LoRA adapters. A new domain-aware supervision...
论文指出 AI 代理现在承担创建 PR、选择依赖、重构代码库、解释测试失败以及执行基础设施变更等任务，但会话一旦结束，它们的推理、决策和工具调用记录就会消失；而 git log 只显示改了什么，不显示哪个模型、调用了哪些工具、谁对结果负责。作者提出 Agentic Process Evidence (APE)，这是一种签名、防篡改、机器可读的代理过程证明，把代理会话与其结果绑定。APE 支持 in-toto 风格证明框架，并支持 Pol...
The paper introduces LoCo, a model-agnostic framework that localizes visual concepts across layers, generation scales and positions in next-scale autoregressive models. It also presents LoCoBench, a dataset spanning 10 c...
This paper analyzes clustered optimal-transport activation steering for toxicity mitigation in Gemma-2-2B and Granite-3.1-2B. It proves that cluster displacements averaged by cluster size equal the standard difference-of...
A compute-matched study reports that synthetic pre-pretraining (PPT) never outperformed pure natural-language training across four curricula (k-Dyck, neural cellular automata, declarative reference corpora and code) and...
Researchers introduced EPC-RawDC, a conditional 3D latent diffusion framework for CBCT-to-CT image synthesis that incorporates scanner-specific acquisition physics rather than relying on image data alone. The method comb...
