… Training on 13 frontier-LLM agents and testing on 91 held-out scaffolded agents, the full model outperforms direct LLM-as-Predictor prompting and game+text features baselines. …
… It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that cover 28 value systems and 332 dimensions. …
…evaluate memory systems' ability to help agents acquire environment-specific experience in web environments, featuring a suite of memory methods including AgentRunbook-R and AgentRunbook-C that demonstrate varying performance in accuracy…
…We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing . We present the Local Communication for Multi-agent Pathfinding (LC…
… The following papers were recommended by the Semantic Scholar API DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data 2026 MTA-Agent: An Open Recipe for Multimodal Deep Search Agents 2026 GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory… …
…We develop an interactive execution environment for agents, featuring a unified action space comprising Clarify, Implement, Verify, and Submit, enabling iterative intent refinement, code synthesis, and visual feedback-based validation. Extensive experiments…
… It features two complementary tasks: Deep Research – tracking down a specific target paper through multi-step reasoning. …
… Finally, empirical results demonstrate improved long-horizon reasoning accuracy and a favorable accuracy-efficiency trade-off compared to state-of-the-art agentic memory systems. …
… It features a hierarchical abstract tree index with different abstraction strategies, enabling efficient and precise retrieval with logarithmic time. …
…Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming . Open-ended coding remains a weak spot for LLMs, largely because…