arXiv:2602. 11198v2 Announce Type: replace-cross Abstract: Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code.
arXiv:2510. 15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke.
The paper introduces ARTEMIS, a no-code evolutionary optimization platform that automatically tunes large language model (LLM) agents by jointly optimizing prompts, tool descriptions, and parameters using semantically-aware genetic operators. Starting from a benchmark script and natural language goals, ARTEMIS discovers configurable components, extracts performance signals from execution logs, and evolves configurations without architectural changes. Experiments on four agent systems show significant gains: a 13.6% increase in acceptance rate for the ALE Agent, a 10.1% performance boost for the Mini‑SWE Agent, a 36.9% token‑reduction for the CrewAI Agent, and a 22% accuracy improvement for the MathTales‑Teacher Agent using a smaller open‑source model.
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
arXiv:2607. 03451v1 Announce Type: cross Abstract: While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines.
The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.
arXiv:2609.09410v1 Announce Type: new Abstract: While autonomous agents have made significant strides in "deep research" by iteratively navigating the open web to synthesize information, real-world p...
arXiv:2609.37172v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuri...
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
arXiv:2607. 14149v1 Announce Type: new Abstract: Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing.
The paper introduces SAEScientist-Bench, a benchmark that tests whether AI agents can autonomously conduct mechanistic interpretability research using Sparse Autoencoders (SAEs). Agents are tasked with designing contrastive probes and navigating a large feature dictionary in Gemma-2-9B-IT to identify optimal features for a target concept, with performance measured against expert-curated references on activation rank, concept selectivity, and causal steering. Results show that while frontier agents can discover features and outperform controls, they still lag behind expert baselines, especially in causal steering, highlighting both the potential and current limitations of closed-loop autonomous AI research.
arXiv:2609.01045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and...
Benchy is a semantic language and execution engine designed to standardize task-oriented AI benchmarks. Each benchmark is fully defined by a program, a scoring function, and a dataset (B=(P,S,D)), and is independent of the AI system that runs it. Benchmarks are authored in canonical YAML, compiled deterministically into JSON, and executed via a universal runtime contract that exposes a named-field input object and a named-field output object, ensuring consistent integration across AI systems.