arXiv Computation and Language
Scaling Discovery Requires Forgetting
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 1
AIM: Agentic Idea Management for Automated Research
arXiv:2609.38445v1 Announce Type: new Abstract: Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven se...
arXiv AI
Oct 15
AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
arXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively,...
arXiv AI
Oct 7
Stateless Language Agents: Scaling Long-Horizon Automated Research
arXiv:2610.07625v1 Announce Type: cross Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay...
Hugging Face Trending Papers
Aug 7
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using agent?
arXiv Computation and Language
3d ago
A-MapReduce: Executing Wide Search via Agentic MapReduce
arXiv:2602.01331v2 Announce Type: replace-cross Abstract: Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize itera...
arXiv Computation and Language
Oct 22
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
The paper proposes a framework for building autonomous AI research teams that can discover linear attention architectures. By assembling agents with diverse disciplinary expertise, private research histories, shared experimental evidence, and adaptive allocation of research opportunities, the team can balance exploration and exploitation under limited experimental budgets. Experiments show that this design outperforms GDN2 at 1.3B scale on language modeling, common‑sense reasoning, and retrieval tasks, and that removing any single component weakens discovery.