The paper introduces AsyncTool, a new benchmark designed to evaluate LLM agents' ability to handle multiple, concurrent tasks with delayed tool feedback, demonstrating that asynchronous coordination i…

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

The paper introduces MAVEN, a lightweight symbolic reasoning scaffold that significantly improves the generalization and end-to-end success rate of large language models in complex, multi-step tool-ca…

This paper proposes a new method for agentic Reinforcement Learning called Agentic Procedural Policy Optimization (APPO) that improves tool-use capabilities by assigning credit to fine-grained decisio…

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex a…

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly impro…

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

The paper proposes ReuseRL, a method that improves agent generalization in Reinforcement Learning by enforcing structural compressibility of successful agent trajectories into reusable skills.

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…

ReSkill is an RL-in-the-loop framework that reconciles skill creation and policy optimization by automatically creating, testing, and refining modular skills alongside the agent's policy learning, lea…

The paper introduces CRAB-Bench and RUSE, a rigorous evaluation framework that tests LLM agents on complex, interdependent tasks with realistic human user interactions, revealing significant performan…

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

HarnessForge introduces a meta-adaptive framework that jointly evolves the execution structure (harness) and the reasoning policy of LLM agents, significantly improving overall system performance acro…

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…