Tool Use & Agents - Weekly Roundup

Protein aggregates merge up to 3.8 times faster in concentrated solutions than standard two-body kinetics predict, an effect captured by replacing zero-dimensional population balance models with dynamic level-set boundary interactions.

Non-linear electrochemical transport equations can now be solved on noisy quantum hardware, unlocking the first end-to-end quantum simulation of an entire battery cell.

This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.

GameDirector is introduced, the first agentic framework that decouples rule-based gameplay logic from visual rendering, allowing players to configure characters, states, and rules much like a game developer while preserving coherent game mechanics.

An agentic building-aware satellite Gaussian Splatting workflow that uses Segment Anything-derived building masks as semantic priors and an Agentic Reconstruction Controller to select, verify, and record DSM reconstruction policies for auditable urban 3D analysis is presented.

This work introduces ACLArena, a framework for comprehensively studying, analyzing, and evaluating Agent Continual Learning, and proposes a new ACL recipe that combines offline replay over high-quality trajectories with a routed network of multiple LoRA experts each specialized via RL, substantially improving the agent's ability to learn across multiple domains.

This work recast black-box black-box LLM steganography as a sequential communication problem with causal, noiseless feedback: every generated token is observed by both parties and can guide subsequent embedding.

Several open research questions are identified, including how to efficiently record incidents and how to determine whether vulnerabilities and incidents generalize, and privacy requirements are summarized and research directions for the secure and trustworthy deployment of AI agents are outlined.

It is concluded that cross-paper ASR comparison is currently unsupported, and a ten-item reporting checklist targeted at each failure is proposed, to supply the shared measurement contract the field has so far done without.

A training-free agentic framework built around specialist detectors, per-detector triage, and conflict-aware evidence arbitration is studied, indicating that the main challenge of open-world image forensics is not detecting manipulations, but calibrating trust in specialized forensic tools and arbitrating conflicting evidence.

Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate, evaluating audio reasoning, multilingual understanding, tool use, conversational behavior, full-duplex interaction, and safety.

This work shows that indirect tipping through intermediate stepping-stone equilibria can reduce the committed minority required to reach an alternative state, bypass majority requirements, and make possible transitions inaccessible through direct challenges.

Document Retrieval-Aware Chunking (D-RAC), an extension of the Web Retrieval-Aware Chunking (W-RAC) framework to arbitrary document formats, is presented, preserving W-RAC's cost, determinism, and observability benefits while unlocking every renderable format as a first-class input.

This work introduces Harness-Zero, which enables harness distillation through agent-as-harness, and shows that for frontier LLMs using the same evolved harness, agent-as-harness outperforms code-as-harness.

VideoGen-Agent is presented, a multimodal agent trained through multitask agentic reinforcement learning to use external tools for video generation to support learning tool use across video-generation tasks and show that the trained agent can benefit from subsequent advances in generation tools.

Regularized Recursive Self-Improvement of Agent Harnesses (RRSI) is introduced, which incorporates the principles of regularizations into harness self-improvement by constraining the evolution candidate proposal and selection.

The contribution of this work is a process-oriented framework that enables AI coding agents to operate with bounded autonomy within an explicit, reviewable, and test-oriented software development lifecycle.

A framework for evaluating vulnerability reports via probes, executable checks of security properties, which surfaced 23 previously unreported vulnerabilities, the majority of which have been confirmed by maintainers.

Jev-Mem is introduced, a new agentic memory architecture inspired by System-One/System-Two cognition, which improves both memory effectiveness and system efficiency.

This work extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure, and validates SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff.

This paper argues that reactive oversight must be complemented by an anticipatory mode: oversight exercised before the agent acts, by specifying the normative agenda that structures the space of permissible action and refining it iteratively through specification, runtime, and inspection.

This work extends FunctionGemma 270M-it to practical Android workflows by introducing MOBILEACTIONSEXTENDED, a synthetic, schema-validated dataset of ~9,500 conversations covering fifteen device-control categories, highlighting compact local function calling as a practical path towards low-latency and privacy-preserving mobile assistants.

Lara, a machine-checkable language and protocol for checking and revising support for research claims, is introduced, and the metatheory of claim checking and cross-context argument transport is established, and semantic guarantees in Lean 4 are mechanized.

MCP-GRANITE is presented, an open-source extensible benchmark framework that treats tool-interface granularity as a controlled variable for MCP-based agents, evaluated under edge and IoT scenarios and identifies tool-interface granularity as a key design parameter for MCP-based agents.