arXiv:2609.00823v1 Announce Type: new Abstract: Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We…
Category: AI
When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection
arXiv:2609.00782v1 Announce Type: new Abstract: Unsupervised feature selection seeks a compact subset of informative features without access to class…
Towards a Reliable and Practical Eval Pipeline
arXiv:2609.00805v1 Announce Type: new Abstract: LLM-based software systems increasingly require effective “evals” as quality gates in the development…
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
arXiv:2609.00787v1 Announce Type: new Abstract: Humans need to study only a handful of well-written textbooks to master a discipline and attempt its…
OpenClaw Releases OpenClaw 2.0: Guided Model Setup, 575 ms Control UI Startup, and One Trust Boundary Per Gateway
The OpenClaw Foundation has released v2026.8.1, which the project calls OpenClaw 2.0: 933 contributors, 569 first-timers, and more than 16,000 pull…
One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning
arXiv:2609.00813v1 Announce Type: new Abstract: While reinforcement learning has enabled LLM-based search agents to invoke external tools, existing…
Vertiv Strikes $1.45B Deal for Microgrid Firm UtilityInnovation Group
Vertiv said on September 2, 2026 that it has entered into an agreement to acquire UtilityInnovation Group, a microgrid and behind-the-meter power…
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
arXiv:2609.00768v1 Announce Type: new Abstract: Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver…
Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs
arXiv:2609.00738v1 Announce Type: new Abstract: Inference-time search with large language models (LLMs) often concentrates on a small set of structurally…
S^3martCirc: Self-supervised Smart Circuit Discovery
arXiv:2609.00755v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text…