Papers arxiv:2604.25135 FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments Published on Apr 28 Submitted by Amir on Apr 30 Authors: Amir Saeidi , , , , , , Abstract Failure-Aware Meta-Agentic framework improves open-source LLM performance in convers… …
… AI-generated summary AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, automating code review acro… …
… To systematically assess generated evaluations, we introduce a meta-evaluation framework alongsideAgentEvalBench, a benchmark comprising 20 agents, each paired with evaluation requirements and test scenarios. …
… View arXiv page View PDF Add to collection Community TLDR: RubricEM introduces a rubric-guided reinforcement learning framework for training long-form deep research agents, enabling finer-grained stagewise credit assignment and reflection meta-policy training beyond verifiable rewards. noticed a po… …
… We propose faithful uncertainty: aligning linguistic uncertainty with intrinsic uncertainty. This is one facet of metacognition -- the ability to be aware of one's own uncertainty and to act on it. …
… AI-generated summary LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. …
… During inference, a fast capability loop updates agent expertise using trajectory-level feedback, while a slow meta-LLM-driven topology loop performs agents’ birth-death operations on MAS, including edge edit, agent addition, and agent removal. …
… AI-generated summary We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes stencils, all-pairs in n-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT . …
… The following papers were recommended by the Semantic Scholar API Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory 2026 MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents 2026 Human-Inspired Memory Architecture for LLM Agents 2026 ByteRover:… …
… AI-generated summary Any new medium, once it emerges, is used for more than the transmission of overt content alone. …