Reframe aligns visual agents on tool observations during distillation
GD-GRPO and observation-gated multi-teacher distillation beat Mix-RL and vanilla MOPD on 14 benchmarks.
Stories per day · 30 days
4 RSS
Relatedreinforcement-learning4grpo2qwen2tool-use2alfworld1browsecomp1context-compaction1credit-assignment1generalization1harness-scaling1lean41llm-agents1multi-session1on-policy-distillation1oracle-continuations1qwen2.51sero1software-engineering1
13 stories, newest first · one card per story
Stories tagged #agentic-rl
Harness Scaling trains agentic RL across diverse harnesses
A factorized training subset improved transfer to unseen white-box setups and external black-box harnesses.
Self-Credit densifies sparse rewards for long-horizon agentic RL
It raises Qwen3 8B and 32B by 37.0 and 36.2 points on BrowseComp-Plus over the base models.
Mosaic: Multi-Session Agentic Reinforcement Learning
Mosaic improves multi-session agentic RL by crediting session contributions instead of broadcasting trajectory advantages.
Lean4AgenticRL trains LAR-9B and LAR-27B with process rewards
Authors report LAR-27B at 77.3% on TerminalBench-2.1 and a 9.89% average gain over the base model.
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
SERO trains long-horizon agents using executable oracle continuations and reachability weighting on ALFWorld and WebShop.
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
MiMo-V2.6 scales reinforcement learning across code, visual, and agent tasks and open-sources the RL stack.
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
NeMo-DCR bit-exactly syncs sparse weight deltas, cutting trillion-parameter refits from 87.5 minutes to 150 seconds.
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
KV-streams stream the KV cache through compaction, speeding agentic RL training 2.6 to 5 times without hurting performance.
PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning
PEARL adapts prefill-decode execution and elastic GPUs, raising agentic RL throughput by up to 2.79x.
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
VHD-Play builds 3,300 agentic RL environments and lifts Qwen3.6-35B-A3B's mean score from 0.204 to 0.815.
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
RetireOPD adds self-retiring on-policy distillation to agentic RL, boosting Qwen2.5 agent success on ALFWorld by 14-19% and WebShop by 12-19%.
Miles v0.1: Production-Level Post-Training
Radix Ark open-sources Miles v0.1, a full-stack RL post-training framework demonstrated with asynchronous agentic RL on GLM-5.2 744B-A40B across 64 GB300 GPUs.