IBM Research

IBM Research on Hugging Face Daily Papers: 14 papers, 0 in the top 3 of their day, 0 paper of the day.

1. DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training 26 upvotes, #17 of 2026-09-04
2. Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents 5 upvotes, #26 of 2026-06-12
3. Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering 4 upvotes, #27 of 2026-06-12
4. Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows 9 upvotes, #27 of 2026-05-27
5. Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents 7 upvotes, #32 of 2026-05-27
6. Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge 10 upvotes, #19 of 2026-05-14
7. MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments 54 upvotes, #7 of 2026-05-13
8. IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance 3 upvotes, #23 of 2026-04-28
9. Efficient Agent Evaluation via Diversity-Guided User Simulation 7 upvotes, #16 of 2026-04-28
10. Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs 85 upvotes, #4 of 2026-03-24
11. VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents 2 upvotes, #33 of 2026-03-18
12. General Agent Evaluation 11 upvotes, #12 of 2026-02-27
13. Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval 2 upvotes, #42 of 2026-02-10
14. SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs 3 upvotes, #34 of 2026-02-09

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.