Instruction-Conditioned Exploration (ICE), which appends one of a small fixed set of instructions to task prompts during training, using the same set for every problem, increasing the coverage of behaviours attempted, improves Qwen3-1.7B held-out pass@1 performance at 4K response length on mathematical reasoning tasks.
Abstract
Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration. New methods are required that leverage the broad knowledge and flexibility of pre-trained LLMs to deliberately generate diverse experience at training time. We propose Instruction-Conditioned Exploration (ICE), which appends one of a small fixed set of instructions to task prompts during training, using the same set for every problem, increasing the coverage of behaviours attempted. To facilitate ICE, we combine RL on the instruction-conditioned policy with self-distillation of its correct rollouts into the unconditioned test-time policy. ICE with this objective improves Qwen3-1.7B held-out pass@1 performance at 4K response length on mathematical reasoning tasks by $5.0\%$ relative to training with DAPO, with improvement persisting at a longer 8K context. The improvement does not appear for Qwen3-4B at 4K, where the instructions do not expand base-model coverage.
Desc descriptive evidence is provided that long-horizon multi-tool post-training can change ways of working that transfer beyond its training domain, and both software-engineering benchmarks improve despite the training collection containing no software-engineering tasks.
Sushant Mehta, Logan Ritchie, Liudas Panavas et al.· 0 citations
This work deconstructs the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface, and uses the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shapes model certainty.
D. Clay, Saket Gollapudi, Sankar V Harilal et al.· 0 citations
SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model, is proposed.
Jinyang Wu, Shuo Yang, Zhengxi Lu et al.· arXiv.org· 7 citations
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards leads to limited guidance on intermediate reasoning processes. Existing approaches such as process reward modeling and on-policy distillation introduce additional constraints, such as reliance on a specialized reward model or assuming identical reasoning patterns between teacher and student. Nevertheless, we observe that once a reasoning process first goes wrong, evaluating the subsequent reasoning provides limited additional information, as it is already conditioned on an invalid prefix. Therefore, we propose Cliff, a reward shaping strategy that utilizes an off-the-shelf LLM as a teacher to identify the first mistake in each rollout. As a result, the rollout is naturally decomposed into two parts: a correct prefix and an incorrect suffix. Cliff then converts this signal into token-level advantages, assigning positive advantages for the correct prefix and negative feedback afterward. Experiments across 12 different scenarios demonstrate that Cliff consistently improves reasoning performance, outperforming on-policy distillation by 15% and standard GRPO by 7%, even with teachers of modest capability. Furthermore, we analyse the role of ``ground truth''in Cliff and investigate its training dynamics. These results establish Cliff as a simple, general and effective approach for improving RLVR with richer, fine-grained supervision.
Peixuan Han, Runnan Wang, Ketan Ramaneti et al.· 1 citation
This work proposes BCSD (Bidirectional Context Self-Distillation), a framework that combines self-distillation with reinforcement learning to train LLM agents to use external skills more effectively, enabling agents to utilize external skills more effectively.
Tian Pan, Yuan Li, Hongda Wang et al.· 0 citations
ADRS is introduced, a framework for constructing return-associated token-level credit for multi-turn language agents that centers and normalizes privileged token scores within each step, modulates them with a return-associated Teacher Value Advantage gate based on within-group confidence--return association, and incorporates the gated token signal into native RL credit construction.
Ran Zhang, Guinan Chen, Chenshaodong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
