arXiv:2512. 11213v2 Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training.
arXiv:2511. 17006v2 Announce Type: replace Abstract: Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool calls that directly constrain environmental interaction.
arXiv:2511. 02734v3 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability.
arXiv:2511. 02200v2 Announce Type: replace Abstract: The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address challenges unattainable for individual models.
arXiv:2606. 05684v1 Announce Type: new Abstract: A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions.
arXiv:2606. 15684v1 Announce Type: new Abstract: We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks.
arXiv:2505. 11765v5 Announce Type: replace-cross Abstract: Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications.
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.
arXiv:2605. 15207v2 Announce Type: replace Abstract: Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines.
arXiv:2606. 01533v1 Announce Type: cross Abstract: Computer use agents (CUAs) today are primarily deployed as single serial agents.
arXiv:2605. 16986v2 Announce Type: replace-cross Abstract: Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability.
arXiv:2608. 04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents.