arXiv:2609.37128v1 Announce Type: new Abstract: Skill evolution improves the capabilities of large language models by analyzing trajectories generated…
Tag: AI
Instinct’s new product recommendations are giving some users the ick
Instinct is rolling out human-curated product and travel recommendations, but some users aren’t happy about getting suggestions they never asked for.
When Should Agents Check External State? Budgeting Observations for Stored Intentions
arXiv:2609.37125v1 Announce Type: new Abstract: Prospective memory allows an agent to retain an intention tied to a future condition, but the stored…
actr: aligning thoughts and responses for multilingual safety in reasoning llms
arXiv:2609.37054v1 Announce Type: new Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their…
Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning
arXiv:2609.37035v1 Announce Type: new Abstract: Streaming video assistance requires models to answer asynchronous questions from an observed prefix under…
Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents
arXiv:2609.37111v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate…
Gemini 3.5 Transcribe vs OpenAI’s GPT-Transcribe
Here’s how each got to where it is, a real use case and working code for both, and a side-by-side on the numbers that actually matter.
MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows
arXiv:2609.37053v1 Announce Type: new Abstract: Multimodal GUI agents have achieved impressive results on general software benchmarks, yet their ability…
Build a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances
Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day…
Breaking the Illusion of Review Reliability under Static Evaluation: SCOPE Fuzzing for LLM-based Scientific Reviewers
arXiv:2609.37097v1 Announce Type: new Abstract: The rapid growth of submissions and reviewing workload has accelerated the use of large language models…
