We have 10 of 21 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.
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts, and Interlock, a framework for task synthesis that represents each task as a typed completion graph is proposed...
This work proposes TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology that explicitly captures how tool invocations and environmental responses drive the divergence between effective strategies and failure modes.
The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for...
COPC is introduced, an actor--critic method combining token-level ratio masking with two-sided clipped-ratio weighting of TD residuals for return and advantage estimation that achieves the highest reported performance on tool-integrated mathematical reasoning and search, outperforming the strongest reported asynchronou...
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agen...
FlexiWorld, a JEPA-based world model that combines mixed-span goal supervision with variable-length action chunks to improve long-horizon control, is introduced and PushT ablations show improved direct control from mixed-span supervision, variable-length chunks, and Student Forcing.
MineExplorer benchmark for evaluating open-world exploration capabilities of MLLM agents in Minecraft is introduced, which first filter atomic tasks whose solutions rely heavily on Minecraft-specific knowledge to better reflect general open-world reasoning and compose atomic tasks into implicit multi-hop tasks.
This paper proposes UrbanGround, the first sandbox to make this question testable in a physically constrained replica of Hong Kong built from territory-wide 3D geospatial data, and hopes it will support broader study of how far current MLLM agents can explore reliably in complex, open-ended urban environments.
CAST (Credit Assignment from Solver Teachers), which converts value changes in a game solver's state value into solver advantages and injects them into RLVR as turn-level signals and achieves the highest average zero-shot performance on ALFWorld and WebShop.
This work proposes AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning that aggregates token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a Bayesian belief state in log-odds space.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
