The paper introduces RoleCDE, a novel benchmark that evaluates role-playing agents' ability to resolve conflicts between role-specific values and general alignment constraints, revealing a 'Role Value…

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 introduces Mindgames, a comprehensive multi-game arena for evaluating LLM agents' sustained social and strategic reasoning, demonstrating that current evaluations are limited by structural s…

The paper introduces PokerSkill, a novel framework that successfully enables Large Language Models (LLMs) to play expert-level poker by grounding their choices using human-designed, rule-based poker s…

The paper introduces FinBoardBench, a novel evaluation suite using financial board games to demonstrate that current LLMs, despite strong static reasoning, fail at complex, dynamic wealth management a…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

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…

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 proposes using GUI agents, both as objective evaluators and subjective playtesters, to significantly improve the generation of playable games from prompts, demonstrating a 66.8% rubric pass-…

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…

The study extends cooperative bias testing across diverse, next-generation LLMs, finding that provider identity is a stronger predictor of cooperative equilibrium than model generation, and that noise…

The paper introduces SPADE-Bench, a new benchmark designed to rigorously evaluate 'agent deception'—the divergence between an agent's reported plan and its actual executed actions—which is a critical…

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…

The paper distinguishes between a model's ability to generate useful updates for external agent components (harness-updating) and its ability to benefit from those updates (harness-benefit), finding t…

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

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 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…

The paper introduces HERO'S JOURNEY, a benchmark for testing complex rule induction in text games, finding that while LLMs show limited rule induction ability, procedural tasks remain a significant ch…

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…

This paper investigates the 'faithfulness gap' in LLM agents—the discrepancy between stated reasoning and actual action—by decomposing it into two opposing steps: reasoning-to-conclusion and conclusio…