We have 6 of 31 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.
Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and...
GraphForge, an evidence-graph based framework that grounds both the task and its verification in real files, and rejects fine-tuning on the SFT model's own rollouts yields further improvements on all three benchmarks, suggesting that the rubrics provide a useful selection signal.
This work proposes AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback, and constructs a diverse asynchronous multitasking dataset that covers multiple scenarios and tool-use patterns.
Video-DR is introduced, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web retrieval, enabling autonomous exploration that breaks the imitation-learning ceiling.
VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought, demonstrates that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.
These results establish source-intent preservation and shared executable-state grounding as key principles for scalable terminal-task synthesis as key principles for scalable terminal-task synthesis.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
