mlsanityData to 14 Oct 2026

Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning

arXiv 2608.16620 ↗First posted 17 Aug 2026cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Supervised Fine-Tuning on a compact corpus of verified, synthetic tool-use trajectories, optimized with a Muon + Adam hybrid. The recipe is deliberately conservative and deliberately controlled: 626 trajectories, a single epoch, a low learning rate, and a KL anchor to the frozen base. The model shows substantial gains over the previous default model for Writer Agent, and compares favorably with several recent models on public benchmarks, scoring the highest on BFCL Core at 0.785 and posts the highest six-benchmark mean of the cohort. Furthermore, the model has shown itself to be competitive or leading relative to comparators in our bias and safety evaluations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 15 of its 20 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

15 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025LIMI: Less is More for Agency22 Sep

Other references · 14

  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,135
  5. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  6. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  7. 2025LIMO: Less is More for Reasoningcited by 498
  8. 2025Muon is Scalable for LLM Trainingcited by 428
  9. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  10. 2026Self-Distillation Enables Continual Learningcited by 247
  11. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 127
  12. 2026IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reusecited by 31
2 more
  1. 2025FORTRESS: Frontier Risk Evaluation for National Security and Public Safetycited by 24
  2. 2025Anchored Supervised Fine-Tuningcited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
  2. 2025Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM
  3. 2026EvalBuilder: Can LLMs Build Efficient Benchmarks?
  4. 2025Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
  5. 2026SPT: Skills as Pre-Training Data for Agentic Language Models
  6. 2026SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale
  7. 2025MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
  8. 2026ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents