模型与评测

T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning

arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many interactive tasks reflect only the final outcome, providing limit

The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating

arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no generation, and is exactly what constrained decoding and likelihood-scoring evaluation harnesses produce. We show that this readout

When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents

arXiv:2610.00372v1 Announce Type: new Abstract: Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Yet recovery is usually judged only by average task success. This hides an import

Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity

arXiv:2609.38659v2 Announce Type: replace-cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For $K$-armed bandits with $A$ optimal arms, we first provid

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

arXiv:2610.00972v1 Announce Type: new Abstract: As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to referenc

DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

arXiv:2610.02161v1 Announce Type: cross Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings. Extending these capabilities to multi-ro

Towards Physical Underwater Robotic Assistance for Scuba Diver Movement in Confined Spaces

arXiv:2610.01906v1 Announce Type: new Abstract: Scuba divers are taught to control their depth to avoid rapid ascents and descents, which could result in serious injuries such as gas embolisms and barotrauma. However, many underwater tasks necessitate lateral control, maintaining

Gemini 4 Argon: our next era of frontier intelligence