Title: SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

Source: http://arxiv.org/abs/2607.03333v1

Summary:

This paper addresses the system-level execution bottleneck of LLM agents by introducing Self-Speculative Forking (SPORK), a training-free controller that enables speculative tool execution. By using the model as its own predictor to dispatch tool calls early and overlap execution with the remaining chain-of-thought decoding, it establishes a foundational efficiency primitive for agentic runtime loops.

Title: No Time Like the Present: Agentic Test-Time Training for LLM Agents

Source: http://arxiv.org/abs/2607.03441v1

Summary:

This paper introduces Agentic Test-Time Training (aTTT), a novel framework that continuously adapts model weights during multi-turn agent episodes to prevent performance degradation over long trajectories. By utilizing a token-level reweighting method to mitigate self-training drift on repeated states, it provides a highly foundational mechanism for sustaining agent reasoning and competence in long-horizon environments.

Title: SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Source: http://arxiv.org/abs/2607.01874v1

Summary:

This paper presents SkillCoach, a framework that self-evolves process-based rubrics to evaluate and supervise complex agentic tool and skill workflows. By decoupling process quality from final outcomes, it provides a foundational mechanism for structured, multi-dimensional trajectory optimization and training of AI agents.

Title: Gemma 4 Technical Report

Source: http://arxiv.org/abs/2607.02770v1

Summary:

This report details Gemma 4, introducing a native thinking mode that allows models to generate structured reasoning traces before responding to queries. It also presents novel compute-efficient Mixture-of-Experts architectures and a unified, encoder-free framework for multimodal ingestion, establishing key primitives for next-generation open models.

Title: The Agentic Garden of Forking Paths

Source: http://arxiv.org/abs/2607.01507v1

Summary:

This paper introduces the Agentic Bootstrap, a foundational paradigm that uses persona-driven AI agents to systematically explore and map the 'multiverse' of alternative analytical decision paths. By formalizing this distribution of defensible choices, it establishes a novel method for validating scientific credibility and mitigating bias in complex agentic decision-making.

Title: Self-Evolving Agents with Anytime-Valid Certificates

Source: http://arxiv.org/abs/2607.00871v1

Summary:

This paper introduces SEA, a novel architectural framework designed to safely enable self-evolving and self-modifying AI agents by confining code changes to a steering adapter governed by anytime-valid certificates. It directly addresses a major safety and stability bottleneck in agentic autonomy by ensuring self-evolution does not cause performance regressions.

Title: Autonomous Scientific Discovery via Iterative Meta-Reflection

Source: http://arxiv.org/abs/2607.01131v1

Summary:

This work proposes DiscoPER, an agentic framework featuring a novel second-order meta-reflection loop that allows agents to treat their own accumulated findings as empirical data to guide future exploration. It introduces a highly sophisticated reasoning primitive for open-ended autonomous discovery, pushing past the limits of traditional static agent reasoning loops.

Title: Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration

Source: http://arxiv.org/abs/2606.31422v1

Summary:

This work introduces a budgeted probing framework to address the critical issue of world-model drift in long-horizon planning agents. By formalizing environment feedback as a scarce calibration resource rather than just a task progression tool, it establishes a foundational method for active belief-state repair and perception in agentic loops.

Title: ACE: Pluggable Adaptive Context Elasticizer across Agents

Source: http://arxiv.org/abs/2606.31564v1

Summary:

This paper proposes a plug-and-play context management module that dynamically orchestrates historical agent trajectories into raw, abstracted, or dropped states. By enabling reversible context compression, it resolves a fundamental bottleneck in long-horizon AI agents where critical historical information is irreversibly lost during standard truncation or summarization.

Title: Self-Evolving World Models for LLM Agent Planning

Source: http://arxiv.org/abs/2606.30639v1

Summary:

This work presents WorldEvolver, a novel framework that equips long-horizon LLM agents with self-evolving world models to enhance predictive planning. By integrating episodic and semantic memories to revise test-time reasoning context dynamically without parameter updates, it establishes a robust new primitive for agent foresight.