Related papers: Milestone-Guided Policy Learning for Long-Horizon …
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…
Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit…
Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and then gradually filling…
Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI collaboration, requiring agents to follow natural language instructions to execute coherent action sequences in complex environments. Existing approaches…
Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness…
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from…
Large language model (LLM) agents are increasingly tested on complex tasks, but their ability to allocate scarce resources over long horizons remains unclear. Unlike reactive tasks with immediate feedback, this setting requires agents to…
Mastering complex sequential tasks continues to pose a significant challenge in robotics. While there has been progress in learning long-horizon manipulation tasks, most existing approaches lack rigorous mathematical guarantees for ensuring…
As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…
In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating…
General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder goals, they demand increasingly stronger agentic capabilities from foundation Large…
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…
The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…
The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history…
Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…
Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool planning is challenging, because the exploration space suffers…
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior…
Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they can extend to extreme…