We have 9 of 84 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment. We propose Recursive Self-Rewrite (RSR), a framework that uses one base model, Qwen-3.8-27B, to discover successful solutions under...
T1, a Mixture-of-Experts model of 122B total trained with reinforcement learning, operating a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier by executing each task's own verifier.
Recursive Synthetic Terminal Tasks (RST) is presented, a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale and shows no ceiling, indicating that the process can continue well beyond the scale reported here.
InComeS is a flexible framework that enhances LLMs'ability to process editing contexts through explicit compression and selection mechanisms, enabling efficient handling of multiple edits without being restricted by the model's context window.
DeepSearch-Evolve is presented, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools that enables scalable self-evolution for long-horizon web agents.
Hierarchical Landmark Sparse Attention is proposed, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-attention counterparts.
This work provides a scalable and effective framework for extending RLVR beyond the limitations of pattern-based verification to complex, noisy, real-world domains, and generalizes strongly to seven out-of-distribution benchmarks.
This paper introduces C LUE (Clustering and Experience-based Verification) , a training-free, non-parametric verifier that improves selection and reranking in Large Language Model outputs and finds that correct and incorrect solutions exhibit measurable geometric differences in their hidden-state trajectories.
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a d...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
