The Morning
From the arXiv
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
ureka orchestrates specialized "Macro-Agents" to tackle complex, long-horizon scientific tasks by dynamically compiling them into obligation graphs. Its core method involves receding-horizon planning and architecture evolution to adapt and optimize agent behavior, leading to highly efficient and reliable task completion. The key contribution is a novel meta-agent framework that demonstrates robust performance and significant computational savings in scientific discovery.
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
MLREF addresses reward function design bottlenecks in RL by treating a persistent pool of reusable reward modules as the primary optimization object. Instead of monolithic reward generation, MLREF constructs rewards as linear combinations of these modules, pro…
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
This paper introduces EvoResearcher, a training-free method that enhances Large Language Model (LLM) reasoning at inference time. It achieves this by enabling a frozen LLM to iteratively generate, self-critique, and revise its responses until a satisfactory an…
A Theory of Post-hoc Debate Judgement
This paper proposes a formal theory for post-hoc debate judgment, aiming to improve reproducibility, robustness, groundedness, and explainability in AI debates. The core method involves identifying and testing formal properties that debate judgment should sati…
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
This paper introduces an Adaptive Memory and Reflection (AMR) multi-agent system for medical question answering. Its core method involves specialized agents with dedicated memory and reflection mechanisms to retrieve prior cases and refine reasoning. The syste…
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
This paper introduces Verifiable Latent Alignments (VLA), a framework to detect and control covert coordination in multi-agent language models by analyzing their hidden communicati…
DentAgent: Evidence-Centric Multi-Agent Coordination for Multimodal Dental Reasoning
DentAgent is an evidence-centric multi-agent framework that addresses limitations in existing dental AI systems by integrating multimodal data. It uses a coordinated system of five…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
This paper introduces Harness Continual Learning (HCL), a new paradigm that enables agents to adapt and improve through changes in their "harness" (prompts, memories, tools, etc.) …
MedUAG: Unified Understanding and Generation for Medical Multimodal Models
This paper introduces MedUAG, a unified framework for medical multimodal understanding and generation. It addresses the lack of comprehensive resources by creating the largest medi…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
This paper proposes rEDMRec, a method to distill LLM reasoning for recommendations into a compact, editable "experience memory." Instead of re-generating expensive reasoning for ea…
The Town Square
Stripe has acquired OpenRouter, a platform that aggregates and provides access to various large language models, aiming to enhance its AI capabilities and offerings.
Workshops
OpenViking is a self-evolving context database that unifies AI agent memory, knowledge retrieval-augmented generation (RAG), and skills for enhanced agent capabilities.
This repository provides a local multi-agent harness, enabling developers to easily set up and run multiple AI agents for testing and experimentation in a controlled environment.
