ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

The paper introduces Sophrosyne, a system that moderates LLM agent exploration in relational data systems, significantly reducing over-exploration and boosting SQL generation accuracy by guiding the a…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

This paper introduces RSIBench-Data, a controlled benchmark for evaluating data-centric research capabilities of LLM agents.

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical st…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in spe…

This paper introduces the Always-On Evaluation Protocol (AOEP-v0) for evaluating always-on agents by focusing on state mutation and recovery obligations.

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

MOSAIC introduces a structured agentic framework that treats automated data science as a staged, context-grounded model selection problem, improving performance and traceability over traditional AutoM…

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

This paper introduces progressive crystallization, a lifecycle for AI agents in IT operations that converts validated agent behaviors into cheaper and more reproducible deterministic workflows, increa…

MemPro introduces a system-level evolution framework that treats the entire memory construction-retrieval pipeline as an evolvable program, significantly improving long-horizon agent performance over…

This paper introduces Retriever, an asynchronous decision model and runtime system for building long-horizon robot agents with explicit clock and input-consumption semantics.

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

This paper introduces ArchEval, a benchmark and platform for evaluating LLM agents on computer architecture design and optimization.

The paper introduces GAIATrace, a comprehensive token-level dataset, and Vidur-Agent, a simulator, to enable reproducible and detailed system-level characterization of complex multi-model agentic AI s…