Paper page - From AGI to ASI
…This report investigates how AI itself might continue to develop in a post-AGI world along the continuum of machine intelligence. The endpoint of this continuum, Universal AI , is theoretically well understood…
Search
Paper page - Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
…an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent R (run as a coding…
Paper page - Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
…Even advanced AI agents function on message exchange formats, successively exchanging messages with users, systems, with itself (i.e. chain-of-thought) and tools in a single stream of computation. This bottleneck…
Paper page - FutureSim: Replaying World Events to Evaluate Adaptive Agents
…Intelligent Systems Authors: , , , , , , , Jonas Geiping Abstract FutureSim enables evaluation of AI agents' long-term predictive capabilities by simulating chronological real-world event sequences, revealing significant gaps in current forecasting performance. AI-generated…
Paper page - AcademiClaw: When Students Set Challenges for AI Agents
…Junjie Yu , , , , , , , , , , , , , , , , , , , , , Abstract AcademiClaw presents a comprehensive benchmark for evaluating AI agents on complex academic tasks spanning multiple domains, revealing significant capability gaps in current models. AI-generated summary Benchmarks within the…
Paper page - RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
…Together, Real ICU provides a clinically grounded testbed for measuring and improving AI sequential decision-support in high-stakes care. Project page: https://chengzhi-leo.github.io/Real ICU -Bench/ View arXiv…
Paper page - Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
…Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields Published on Jun 9 Submitted by taesiri on Jun 10 ByteDance Seed Authors: , Jingzhe Ding , , , , , , , , , , , , , , , , , , , , Abstract Current AI…
Paper page - Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
…2 Om AI Lab Authors: , , , Abstract A systematic comparison of vision-language models and video generation models reveals complementary strengths for spatial intelligence tasks, with vision-language models excelling in semantic tagging…
Paper page - Reducing Political Manipulation with Consistency Training
…28 Submitted by Long Phan on May 29 Center for AI Safety Authors: , , , , , Abstract Large language models demonstrate systematic political bias in handling opposing viewpoints, which can be mitigated through a reinforcement…
Paper page - EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
…Jiaqi Liu , , , , , , Abstract EvolveMem enables adaptive memory systems for LLM agents through self-evolving retrieval mechanisms that autonomously optimize configuration parameters via diagnostic modules and iterative research cycles. AI-generated summary Long…