arXiv Machine Learning
How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
23h ago
Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
The paper investigates how the representation of tool interfaces—referred to as a tool schema—affects the performance of large language model agents. By systematically transforming a native tool schema with nine operators, the authors demonstrate that agents exhibit significant variability in success rates across different but functionally equivalent schema variants, a phenomenon they call schema bias. Experiments on eleven LLMs, including closed models, reveal that success can range from complete failure to 97% solely due to schema differences, and that training only mitigates bias when the specific variant is included in the training data.
arXiv AI
Jul 21
Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking
arXiv:2607. 17948v1 Announce Type: new Abstract: Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making, while complex collective behavior emerges from interactions among agents.
arXiv AI
Sep 24
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
The paper introduces JAZ, a minimalist LLM agent framework that centers on a single primitive called “invoke”, which allows an LLM to write and execute arbitrary code, including recursive calls, while treating all inputs and interaction history as variables in the code environment. JAZ provides built‑in hooks for constraints and monitoring but relies solely on prompting, without external tools, memory systems, or file‑system access. Experiments show that JAZ “invoke” outperforms specialized external harnesses such as Letta (MemGPT) and ACE on long‑horizon recall tasks and continual self‑improvement, achieving higher accuracy at lower cost.
arXiv AI
Jul 29
Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL
arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.
arXiv Machine Learning
Jun 8
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
arXiv:2512. 13278v2 Announce Type: replace-cross Abstract: Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use.
arXiv AI
Aug 5
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
arXiv:2608. 03327v1 Announce Type: new Abstract: Hybrid computer-use agents can act through screenshots or call text tools.