Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Paper • 2610.08077 • Published 4 days ago • 137
CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution Paper • 2610.10426 • Published 3 days ago • 9
Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion Paper • 2606.14885 • Published Jun 12 • 13
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Paper • 2610.08077 • Published 4 days ago • 137
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 64
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 64
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction Paper • 2605.05242 • Published May 3 • 126
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published Mar 17 • 103
Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute Paper • 2506.15882 • Published Jun 18, 2025 • 2
Where LLM Agents Fail and How They can Learn From Failures Paper • 2509.25370 • Published Sep 29, 2025 • 12
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs Paper • 2509.22646 • Published Sep 26, 2025 • 17
TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning Paper • 2510.06217 • Published Oct 7, 2025 • 66
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use Paper • 2510.05592 • Published Oct 7, 2025 • 113
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention Paper • 2303.16199 • Published Mar 28, 2023 • 5
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models Paper • 2304.09842 • Published Apr 19, 2023 • 2
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts Paper • 2310.02255 • Published Oct 3, 2023 • 2