HyperTool: Unified executable MCP-style interface reduces step-wise tool call overhead for LLM agents
HyperTool introduces a unified executable interface that allows LLM agents to invoke multiple tool calls within a single code block, hiding intermediate dataflow from the main reasoning trace. This addresses an 'execution-granularity mismatch' where step-wise atomic tool calls waste context and force models to manage low-level operations. On the MCP-Universe benchmark, HyperTool more than doubles accuracy for Qwen3-32B (15.69% → 35.29%) and Qwen3-8B (9.93% → 33.33%), outperforming GPT-OSS and Kimi-k2.5.
Related guides (3)
Related events (8)
PROVE framework trains LLMs for multi-step tool use via stateful MCP environments and programmatic rewards
Researchers introduce PROVE (Programmatic Rewards On Verified Environments), a framework for training LLMs to orchestrate multi-step tool calls using reinforcement learning. The system includes a library of 20 stateful MCP servers with 343 tools, an automated data synthesis pipeline that grounds training queries in live server state, and a multi-component programmatic reward function requiring no judge model. Training four models (Qwen3-4B, Qwen3-8B, Qwen2.5-7B, Granite-4.1-8B) with ~13K examples yields gains of up to +10.2 on BFCL Multi-Turn, +6.8 on tau2-bench, and +6.5 on T-Eval, demonstrating consistent improvements in multi-step tool orchestration.
Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
This paper introduces IH-GRPO, a reinforcement learning algorithm that decouples tool invocation from immediate execution during LLM reasoning, addressing the coherence disruption caused by tight coupling in existing tool-integrated reasoning (TIR) approaches. The authors propose a hierarchical control framework and derive a surrogate loss enabling an implicitly hierarchical policy to match the behavior of an explicit hierarchical policy. Experiments on Qwen3 models (1.7B, 4B, 8B) show absolute improvements of 1.87–2.53% across six out-of-domain mathematical reasoning benchmarks over the strongest baseline. Code is publicly released.
Tool Use, Unified — Hugging Face Blog
Hugging Face published a blog post addressing the fragmented landscape of tool/function-calling interfaces across different LLMs and frameworks. The post likely introduces or advocates for a unified approach to tool use in the Hugging Face ecosystem, covering how different models expose tool-calling capabilities and how to standardize them. This is relevant to the agent and tooling ecosystem as interoperability between models and tool-calling conventions remains a key friction point.
PhysTool-Bench reveals severe gaps in MLLM physical tool use and embodied planning
Researchers introduce PhysTool-Bench, the first benchmark evaluating multimodal LLMs on physical tool use across 2,510 queries and 2,678 real-world tools spanning manufacturing, electrical work, agriculture, and healthcare. Evaluation of 13 leading MLLMs shows even the best model (Gemini-3.1-Pro) identifies only 58.7% of tools in a scene and completes just 21.0% of queries end-to-end. The results expose a two-level deficit: poor tool perception in realistic scenes and a much larger drop at the planning stage, indicating a lack of functional commonsense for mapping tools to task semantics. This pinpoints a critical bottleneck for embodied AI development.
HexStrike AI: MCP server exposing 150+ cybersecurity tools to AI agents
HexStrike AI is an open-source MCP server that enables AI agents (Claude, GPT, Copilot, and others) to autonomously invoke over 150 offensive security tools for penetration testing, vulnerability discovery, and bug bounty automation. The project bridges LLMs with real-world offensive security capabilities via the Model Context Protocol. With 9,221 GitHub stars, it represents a notable community signal around agentic security tooling and the expanding attack surface of AI-driven automation.
HiViG: History-aware visually grounded critic improves computer use agents across GUI benchmarks
Researchers introduce HiViG, a test-time framework for Computer Use Agents that addresses two weaknesses in existing critic models: short-sighted decision loops and lack of visual grounding. The system trains a multimodal critic on real GUI trajectories to maintain a compact macro-action history and verify execution coordinates against live screenshots before action execution. Evaluated on web, mobile, and desktop benchmarks, HiViG improves average success rates by 5.8% over the strongest baseline with Qwen3-VL-32B and 9.0% with Gemini-3-Flash, with both history and grounding components shown to be independently necessary.
AXPO: Agent Explorative Policy Optimization Addresses Thinking-Acting Gap in Multimodal Agentic Reasoning
This paper identifies a structural asymmetry in agentic reasoning called the 'Thinking-Acting Gap,' where tool use is attempted in only ~30% of rollouts under standard RL training (GRPO), and all-wrong tool-using subgroups suppress learning signals. The authors propose AXPO (Agent eXplorative Policy Optimization), which fixes the thinking prefix and resamples tool calls for all-wrong subgroups, combined with uncertainty-based prefix selection. Evaluated across nine multimodal benchmarks on Qwen3-VL-Thinking at multiple scales, SFT+AXPO outperforms SFT+GRPO by +1.8pp on both Pass@1 and Pass@4 at 8B, with the 8B model surpassing the 32B baseline on Pass@4 using 4× fewer parameters.
Kimi K2.6: Moonshot AI's 1T-Parameter Vision-Language Model Matches Open-Weights Peers, Trails Top Closed Models
Moonshot AI released Kimi K2.6, a 1 trillion-parameter mixture-of-experts vision-language model with 32B active parameters, designed for long-horizon autonomous coding sessions lasting multiple days and multi-agent orchestration scaling to 300 parallel subagents executing up to 4,000 steps. The model matches Qwen3.6 Max Preview and DeepSeek-V4-Pro on the Artificial Analysis Intelligence Index (scoring 54 vs. their 52) while trailing closed models like GPT-5.5 and Claude Opus 4.7. Weights are freely downloadable from Hugging Face under a modified MIT license permitting commercial use, with API access priced at $0.95/$0.16/$4.00 per million input/cached/output tokens. Notable features include a 256K token context window, native INT4 quantization, a 'preserve thinking' mode for multi-turn reasoning continuity, and a research preview 'claw groups' feature enabling cross-developer agent collaboration.