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 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…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

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…

This paper investigates whether adults' struggles with conjunctive causal rules persist when they have agency through active exploration.

This paper investigates whether adults' struggles with conjunctive causal rules persist when they have agency through active exploration.

COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

The paper introduces LinTree, a method that explicitly structures the search history of LLM reasoning traces using parent pointers, significantly improving task performance and search efficiency compa…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

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…

This paper localizes the attention heads within LLMs responsible for specific reasoning steps, finding that specialized heads handle factual retrieval while higher layers manage global information int…

This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.

The paper introduces MineExplorer, a new benchmark in Minecraft, to evaluate the sustained open-world exploration capabilities of MLLM agents, finding that long-horizon coordination remains a signific…

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost…

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…

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…