Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were design...
arXiv:2610.15924v1 Announce Type: cross Abstract: Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. V...
arXiv:2610.16027v1 Announce Type: cross Abstract: Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed er...
arXiv:2610.16071v1 Announce Type: cross Abstract: Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes. Thes...
arXiv:2610.16985v1 Announce Type: cross Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel...
arXiv:2610.16449v1 Announce Type: cross Abstract: Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency fund flows. Existing Graph Neu...
arXiv:2610.14772v2 Announce Type: new Abstract: Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for future camera-first agents is not recognition ab...
arXiv:2610.18484v1 Announce Type: new Abstract: Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution...
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
HarnessMDP is a learning-based framework that treats the execution harness of large language model agents as a learnable control layer. By formulating agent execution as a finite-horizon Markov decision process, the harness learns to select structural execution actions from the evolving agent state, using offline reinforcement learning from collected trajectories. Experiments on coding tasks, tau-bench, AgentBench, and other evaluation settings show that HarnessMDP consistently improves execution behavior and final task performance over baseline harnesses.
arXiv:2610.17867v2 Announce Type: cross Abstract: Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. Ho...
arXiv:2610.17544v1 Announce Type: cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted me...
The paper examines allocation mechanisms that rely on manipulable characteristics and shows that naive optimal rules lead to falsification and inefficiency. It characterizes optimal falsification‑proof rules across various falsification technologies and identifies an honesty condition under which these rules solve the planner’s unconstrained problem of maximizing a weighted sum of allocative surplus and agents’ welfare.
arXiv:2610.15409v1 Announce Type: new Abstract: Enterprise agents need retrieval evaluation sets that expose domain-specific failures and guide developers towards efficient deployment tradeoffs. Neit...
arXiv:2610.20327v1 Announce Type: new Abstract: India's 22 scheduled languages are spoken by over a billion people in conversations that mix languages, often within one turn, overlap freely, and take...
arXiv:2610.16859v2 Announce Type: replace Abstract: For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task mu...
arXiv:2610.17748v1 Announce Type: cross Abstract: Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-hor...
arXiv:2610.16397v1 Announce Type: new Abstract: We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environ...
arXiv:2610.17726v1 Announce Type: cross Abstract: Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new...
arXiv:2610.16895v1 Announce Type: new Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating...