Tools & MCP research

The frontier

Latest Paper· Reinforcement learningMETA ▲0.3%

Training LLMs as adaptive solvers for industrial-scale optimization

The authors propose Strategy-Diverse Reinforcement Learning (SDRL) to train open-source LLMs as adaptive meta-solvers for industrial-scale optimization. They show that combining solver-integrated reasoning, exact algorithms, and heuristic search with a hierarchical diversity reward allows the model to select the best strategy for each problem, outperforming DeepSeek-V4-Pro and GPT-5.5 on average across benchmarks and on industrial-scale tasks.

Shihao Zhang, Weiting Liu, Siyu Shao +4

Code & software

Visual feedback boosts software engineering agent success rates

The authors introduce CUA-SWE, a benchmark and evaluation pipeline for software engineering with computer use. They find that frontier agents which can view and interact with application interfaces complete tasks more successfully than agents limited to code editing, especially in web and game domains.

today

Agents

Evolved prover interfaces make theorem-solving agents faster and cheaper

Viennot, Baudart, and Lelarge treat the interface between an AI agent and a proof assistant as an optimization target. Their evolutionary process built rocq-mcp-evolve, a set of agent-facing tools that outperformed both a compiler-only interface and an established Rocq server across four language models.

yesterday

Safety & security

Execution-Time Checks Limit Malicious Tool Calls by LLM Agents

Li and colleagues address prompt injection in tool-using agents, where poisoned webpages, tool descriptions, memories or reusable skills can induce consequential actions. Their PACE system mediates calls immediately before execution, blocking effects that cannot be justified by the authenticated request while largely preserving normal task performance.

yesterday

Safety & security

Tool-calling agents access more private data than requests require

Zhang et al. test whether tool-calling agents limit themselves to the private data explicitly needed for a user’s request. In a controlled 720-episode benchmark, every evaluated model exceeded the reference scope, while a zero-shot filtering method substantially reduced unnecessary calls.

yesterday

Agents

Training Forecasters to Search Improves Calibration and Reduces Tool Use

Afifi et al. trained an agent to research and forecast resolved real-world events, rather than supplying it with evidence collected in advance. On 265 held-out Polymarket questions, the resulting policy improved calibration by 30 to 40 percent, searched less often, and narrowly outscored four tested frontier models under the same evidence-based forecasting harness.

yesterday

Agents

Active audio-visual tool use improves reasoning across long recordings

Wang and colleagues turn an omni-modal language model into an agent that chooses when to listen, when to look, and which temporal window to inspect. Trained on 170,000 synthetic reasoning trajectories and refined with reinforcement learning, the system reportedly improves performance across audio-visual benchmarks while reducing reliance on single-modality shortcuts.

yesterday

All Tools & MCP papers →

Every paper read and written up by the research desk from the daily arXiv scan · threads are maintained lines of inquiry with running syntheses