…Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability Published on Jun 17 Submitted by haipengluo on Jun 18 Tencent Hunyuan Authors: Haipeng Luo , , , , , , Abstract GRPO algorithms face policy entropy collapse…
…when an object slips, the robot pose drifts, or the scene changes during execution, the policy may continue executing stale actions before querying the model again. VLA-Corrector addresses this issue without…
…World Changes for Robotic Action (2026) Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination (2026) LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies (2026…
…The system produced 7.5M agent invocations , roughly 300K onchain actions, about $20M in volume, more than 5,000 ETH deployed, roughly 70B inference tokens , and 99.9% settlement success for policy…
…Diverse Parallel Exploration Policy Optimization for LLM-based Agents (2026) GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning (2026) FIPO: Eliciting Deep Reasoning with Future-KL…
…Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging (2026) STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models (2026) OPOD: On-Policy…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen…
…on the student's future improvement rather than its immediate loss change, addressing the delayed credit assignment induced by on-policy distillation. Experiments on AIME 24, AIME 25, and HMMT 25 across…
…A promising alternative leverages the per-turn change in the policy's predicted probability of the ground-truth, termed Information Gain (IG), as an intrinsic process signal without an external evaluator. However…
…MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments . Instead of materializing each policy as a merged full checkpoint , MinT keeps the…