# Tool Use in Language Models: Research Digest

> Foundational work set up self-taught tool use, large-scale tool datasets and function-calling benchmarks. Recent preprints focus on distilling agents, adversarial safety training and agents that build their own tools.

- **Canonical:** https://agentflare.org/scholar/tool-use-in-language-models-research-digest.html
- **Updated:** 2026-10-16
- **Category:** scholar
- **Full structured data:** `/scholar/tool-use-in-language-models-research-digest.data.json` — $0.02 via AISA HTTP 402 (https://esa.aisa.one/api/v1/access/verify; agents set crawlerAutoPrice=true)

## Key data

- **Field:** tool use and function calling in language models
- **Foundational:** 10
- **Recent (arXiv):** 8
- **Updated:** 2026-10-16

Foundational work set up self-taught tool use, large-scale tool datasets and function-calling benchmarks. Recent preprints focus on distilling agents, adversarial safety training and agents that build their own tools.

_…full analysis and the complete dataset are available to agents for $0.02 — fetch `/scholar/tool-use-in-language-models-research-digest.data.json` (HTTP 402)._

## Sources

1. [The berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models](https://openreview.net/forum?id=2GmDdhBdDk)
2. [Tool learning with large language models: A survey](https://link.springer.com/article/10.1007/s11704-024-40678-2)
3. [Toolllm: Facilitating large language models to master 16000+ real-world apis](https://proceedings.iclr.cc/paper_files/paper/2024/hash/28e50ee5b72e90b50e7196fde8ea260e-Abstract-Conference.html)
4. [Toolformer: Language models can teach themselves to use tools](https://proceedings.neurips.cc/paper_files/paper/2023/hash/d842425e4bf79ba039352da0f658a906-Abstract-Conference.html)
5. [Large language models as tool makers](https://proceedings.iclr.cc/paper_files/paper/2024/hash/ed91353f700d113e5d848c7e04a858b0-Abstract-Conference.html)
6. [Function calling in large language models: Industrial practices, challenges, and future directions](https://dl.acm.org/doi/abs/10.1145/3788284)
7. [Nexusraven: a commercially-permissive language model for function calling](https://openreview.net/forum?id=5lcPe6DqfI)
8. [Toolrm: Outcome reward models for tool-calling large language models](https://arxiv.org/abs/2509.11963)
9. [Hammer: Robust function-calling for on-device language models via function masking](https://arxiv.org/abs/2410.04587)
10. [Lost in execution: On the multilingual robustness of tool calling in large language models](https://aclanthology.org/2026.acl-long.2039/)
11. [ActionOPD: Distilling Decisions, Not Tokens](https://arxiv.org/abs/2610.19820v1)
12. [Function-Space Temporal Self-Distillation for Policy Optimization](https://arxiv.org/abs/2610.19687v1)
13. [ActICL: Post-Training for Agentic Multimodal In-Context Learning](https://arxiv.org/abs/2610.19475v1)
14. [VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness](https://arxiv.org/abs/2610.19424v1)
15. [AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety](https://arxiv.org/abs/2610.19422v1)
16. [SEAR: Self-Evolving Agentic Robotics](https://arxiv.org/abs/2610.18792v1)
17. [SolBehave: Evaluating the Behavioural Correctness of LLM-Generated Smart Contracts](https://arxiv.org/abs/2610.18745v1)
18. [Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve](https://arxiv.org/abs/2610.18616v1)

## Related

- [LLM Agents & Planning: Literature Digest](https://agentflare.org/scholar/llm-agents-planning-literature-digest.html)
- [Retrieval-Augmented Generation: Research Digest](https://agentflare.org/scholar/retrieval-augmented-generation-research-digest.html)
- [AI Alignment & Safety: Research Digest](https://agentflare.org/scholar/ai-alignment-safety-research-digest.html)
- [RLHF: Research Digest](https://agentflare.org/scholar/rlhf-research-digest.html)
- [Multimodal Foundation Models: Research Digest](https://agentflare.org/scholar/multimodal-foundation-models-research-digest.html)
- [Mechanistic Interpretability: Research Digest](https://agentflare.org/scholar/mechanistic-interpretability-research-digest.html)

---
_Part of AgentFlare, an agent-native data network powered by AISA. https://aisa.one/docs_