arxiv arXiv cs.CL · 51d ago · research

Training LLMs for Long-Lifecycle Agents via Cross-Domain Generalization

from English

A new framework enables large language models to learn 'Connect the Dots' by using reinforcement learning with long rollout sequences. The method includes tailored tasks and environments to foster meta-capability development, showing strong cross-domain generalization and performance in out-of-distribution settings. Implementations are available at https://github.com/agentscope-ai/Trinity-RFT/tree/research/cod/examples/research_cod.

Importance 2/3 New harness with differentiators arXiv cs.CL Allen AI Hugging Face AI agents Reasoning models Training methods

Read original

arxiv arXiv cs.LG · 51d ago · 2 views

Training LLMs for Long-Lifecycle Agents via Cross-Domain Generalization

A new framework enables large language models to develop 'Connect the Dots' capability, allowing long-lifecycle agents to learn from experiences and iteratively update their environment context. The framework uses reinforcement learning with long rollout sequences and custom tasks to promote cross-domain generalization, showing effective out-of-distribution performance in both domains and transition settings.

arxiv arXiv cs.CL · 51d ago · 1 view

H-RePlan: Hierarchical Recovery for Cross-Device Agent Systems

H-RePlan introduces a hierarchical replanning framework that separates device-local strategy recovery from global orchestrator replanning. It outperforms existing baselines by achieving higher completion and instruction adherence, with reduced token cost, through scope-aware recovery in multi-device agent systems.

arxiv arXiv cs.AI · 51d ago

RACL: Reasoning-Agent Control Layer for Metaheuristic Learning

RACL introduces a reasoning agent that controls metaheuristic search behavior without replacing optimizers or altering constraints. It improves or ties key policies in vehicle routing experiments, reducing average cost by 8.337% versus Fixed and 1.605% versus Stagnation-Triggered policies, with no significant computational overhead.

arxiv arXiv cs.LG · 52d ago

Act2Answer Evaluates Knowledge Retention in Vision-Language-Action Models

Act2Answer introduces a lightweight protocol to assess commonsense and world knowledge retention in VLA models by requiring agents to answer questions through object placement actions. A large-scale study of 7 VLA models and 9 VLM baselines reveals that VLAs perform well on simple concepts but show larger gaps on rich semantic categories compared to their source VLMs, with VQA co-training improving knowledge retention and peak answer-relevant signals observed in middle VLA layers.

arxiv arXiv cs.AI · 52d ago · 1 view

Reinforcement Learning Foundation Models Should Already Be A Thing

Reinforcement learning lacks foundation models despite synthetic MDPs being feasible. A proof-of-concept shows a single model trained on synthetic MDPs solves tabular benchmarks without tuning, outperforming existing methods in online settings and matching them offline.