mlsanityData to 7 Oct 2026

Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling

arXiv 2511.05951 ↗First posted 8 Nov 2025cs.AIcited by 6

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Despite the proliferation of powerful agentic models, the lack of critical post-training details hinders the development of strong counterparts in the open-source community. In this study, we present a comprehensive and fully open-source pipeline for training a high-performance agentic model for interacting with external tools and environments, named Klear-Qwen3-AgentForge, starting from the Qwen3-8B base model. We design effective supervised fine-tuning (SFT) with synthetic data followed by multi-turn reinforcement learning (RL) to unlock the potential for multiple diverse agentic tasks. We perform exclusive experiments on various agentic benchmarks in both tool use and coding domains. Klear-Qwen3-AgentForge-8B achieves state-of-the-art performance among LLMs of similar size and remains competitive with significantly larger models.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 37 references that are in the map. First posted on arXiv 8 Nov 2025.

Builds on

28 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework5 Oct
  2. 2025Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents17 Sep
  3. 2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use26 Aug

Other references · 25

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  8. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  10. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  11. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  12. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
13 more
  1. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  2. 2025SWE-smith: Scaling Data for Software Engineering Agentscited by 255
  3. 2025Small Language Models are the Future of Agentic AIcited by 254
  4. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 205
  5. 2025Deep Think with Confidencecited by 199
  6. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certaintycited by 182
  7. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplaycited by 158
  8. 2025Llama-Nemotron: Efficient Reasoning Modelscited by 151
  9. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  10. 2025Scaling Agents via Continual Pre-trainingcited by 39
  11. 2025RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Trainingcited by 31
  12. 2025SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositoriescited by 30
  13. 2025Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystemcited by 28
  2. 2026SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agentscited by 12
  3. 2026SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Testscited by 4
  4. 2026SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Trainingcited by 1
  5. 2026Context-Aware RL for Agentic and Multimodal LLMscited by 0
  6. 2026SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenTinker: Separating Concerns in Agentic Reinforcement Learning
  2. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
  3. 2026Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
  4. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  5. 2026Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
  6. 2026Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
  7. 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
  8. 2026Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement