Agentic AI and the next intelligence explosion
@dair_ai
-
Multi-Agent Self-Evolution for LLM Reasoning
By
–
// Multi-Agent Self-Evolution for LLM Reasoning // Most self-play methods for LLM reasoning lack explicit planning and quality control. This leads to unstable training on complex multi-step tasks. New research introduces a cleaner closed-loop approach. SAGE co-evolves four
-
Survey on Workflow Optimization for LLM Agents
By
–
Great survey on Workflow Optimization for LLM Agents.
-
Agent Memory Systems and Cross-Model Transfer Challenges
By
–
Agents build useful memory during tasks, but that memory is trapped. So the big question is whether a single memory system can be shared across different models. If you want to transfer it to a different model, the performance often gets worse, not better. New research tackles
-
BIGMAS Improves LLM Agents Beyond Reasoning Complexity Limits
By
–
Even the best reasoning models hit an accuracy collapse beyond a certain problem complexity. Giving an LRM the exact solution algorithm doesn't fix it either. This new work, BIGMAS, improves LLM agents by taking inspiration from the human brain. BIGMAS outperforms both ReAct
-
Extracting Agent Skills from Open-Source Code Repositories
By
–
GitHub already has millions of repos full of procedural knowledge. The work introduces a framework for extracting agent skills directly from open-source repos. The pipeline analyzes repo structure, identifies procedural knowledge through dense retrieval, and translates it into
-
Top AI Papers Weekly: KARL, OpenDev, SkillNet, FlashAttention-4
By
–
The Top AI Papers of the Week (March 9 – March 15) – KARL
– OpenDev
– SkillNet
– Memex(RL)
– AutoHarness
– FlashAttention-4
– The Spike, the Sparse, and the Sink Read on for more: -
Continual Learning Experience Skills Multimodal Agents
By
–
Continual Learning from Experience and Skills for Multimodal Agents
-
RL Fine-tuning Generalization Challenges for LLM Agents
By
–
New research on LLM Agent Generalization. RL fine-tuning makes agents strong in familiar environments, but it struggles to transfer across unseen ones. This paper systematically studies RL generalization for LLM agents across three axes: within-environment transfer across task
-
IBM Research Self-Improving Agents Framework Addresses Amnesia Problem
By
–
New research from IBM Research on Self-Improving Agents. Agents have "amnesia." An agent that struggles with a particular API authentication flow today will struggle with the same flow tomorrow unless manually updated. This paper introduces a framework for automatically