10. Fundamental Limits of LLMs at Scale Establishes mathematical foundations for theoretical limitations constraining LLMs: hallucination, context compression, reasoning degradation, retrieval fragility, and multimodal misalignment.
@dair_ai
-
LAMP: Language-Augmented Multi-Agent Reinforcement Learning Pipeline
By
–
9. LAMP: Language-Augmented Multi-Agent RL LAMP integrates natural language processing into multi-agent reinforcement learning through a three-stage pipeline.
-
Dr. MAMR: Solving Lazy Agent Problem in Multi-Agent LLM
By
–
10. Unlocking the Power of Multi-Agent LLM for Reasoning Introduces Dr. MAMR, which addresses the “lazy agent” problem in multi-agent LLM reasoning through Shapley-inspired causal influence measurement and verifiable restart mechanisms.
-
Differentiable Artificial Life Framework for Continuous Agent Learning
By
–
9. PD-NCA
— DAIR.AI (@dair_ai) 9 novembre 2025
A differentiable artificial life framework where multiple independent agents continuously update their parameters through gradient descent during simulation, enabling within-lifetime learning and open-ended behavioral change.https://t.co/0omPU6a4Un9. PD-NCA A differentiable artificial life framework where multiple independent agents continuously update their parameters through gradient descent during simulation, enabling within-lifetime learning and open-ended behavioral change.
-
AlphaEvolve: AI Autonomously Discovers Mathematical Constructions
By
–
8. Mathematical Exploration at Scale Terence Tao and colleagues apply AlphaEvolve, an AI system using LLM-guided evolutionary search to autonomously discover mathematical constructions across analysis, combinatorics, geometry, and number theory.
-
Diffusion Language Models Outperform Autoregressive With Limited Data
By
–
7. Diffusion LMs are Super Data Learners Researchers from NUS, Sea AI Lab, StepFun, and collaborators demonstrate that diffusion language models (DLMs) consistently outperform autoregressive models when unique training data is limited.
-
Unified Tool-Agent Retrieval Framework for Multi-Agent Systems
By
–
6. Tool-to-Agent Retrieval Introduces a unified retrieval framework that embeds both tools and agents in a shared vector space with metadata relationships, enabling efficient routing in multi-agent systems coordinating hundreds of MCP servers and tools.
-
DreamGym: Scaling Agent RL via Experience Synthesis
By
–
3. Scaling Agent RL via Experience Synthesis Meta researchers introduce DreamGym, a unified framework that synthesizes diverse training experiences to enable scalable reinforcement learning for LLM agents without costly real-environment rollouts.
-
Context Engineering Evolution: From Computing 1.0 to Intelligent Agents
By
–
2. Context Engineering 2.0 Traces the 20+ year evolution of context engineering, reframing it as a fundamental challenge in human-machine communication spanning from primitive computing (Era 1.0) to today’s intelligent agents (Era 2.0) and beyond.
-
Google DeepMind Introduces IMO-Bench for Mathematical Reasoning
By
–
1. Towards Robust Mathematical Reasoning Google DeepMind introduces IMO-Bench, a comprehensive suite of benchmarks vetted by IMO medalists targeting International Mathematical Olympiad-level reasoning.