arXiv AI June 15, 2026 By Zhongyuan Wang, Pratyusha Vemuri

When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More

arXiv:2606. 14476v1 Announce Type: new Abstract: A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 6

Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools

arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.

By Atul Anand, Sourav Chattaraj

llms agents benchmarks safety

arXiv AI

Jul 7

The Remarkable Effectiveness of Providing AI Agents with Natural Language Tools: A Replication Study Validating NLT Performance Across 14 Models

arXiv:2607. 03953v1 Announce Type: cross Abstract: This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.

By Alexander Somma, Isabelle Plante, Fred Premji

llms agents

arXiv AI

Aug 5

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.

By Salma El Yadouni (EPFL), Guanyi Li (Binome Technologies)

llms agents benchmarks

Hugging Face Trending Papers

Jul 13

Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results

Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plausible responses. We study inference-time feed-forward network (FFN) intervention for improving structured outputs without retraining model weights.

llms agents

arXiv AI

Jun 2

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).

By Prateek Kumar Sikdar

llms agents fine-tuning

arXiv AI

Jul 15

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

arXiv:2607. 12463v1 Announce Type: new Abstract: Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction.

By Yubo Wang, Jiarong Liang, Yuxuan Zhang, Xuye Liu, Cong Wei, Yuyu Zhang, Ping Nie, Wenhu Chen

agents benchmarks safety

Related stories

Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools

The Remarkable Effectiveness of Providing AI Agents with Natural Language Tools: A Replication Study Validating NLT Performance Across 14 Models

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models