Thinking mode in Qwen3 models improves class-level performance on planning constraints but worsens precision constraints in IFEval, with 10-20% prompt-level flips and directional consistency in Hunyuan models.
Scaling reasoning, losing control: Evaluating instruction following in large reasoning models.arXiv preprint arXiv:2505.14810
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Refusal steering works on MoE LLMs; expert-aware variants succeed with single-expert outputs and refusal signals differ from routing patterns.
ImpRIF improves LLM complex instruction following by synthesizing data from reasoning graphs and training models to reason explicitly along those graphs.
Retrieval-of-Thought organizes prior reasoning into a thought graph for retrieval and reward-guided recombination, reducing output tokens by up to 40% and latency by 82% while preserving accuracy on reasoning benchmarks.
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.
Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following
Thinking mode in Qwen3 models improves class-level performance on planning constraints but worsens precision constraints in IFEval, with 10-20% prompt-level flips and directional consistency in Hunyuan models.
-
Expert-Aware Refusal Steering
Refusal steering works on MoE LLMs; expert-aware variants succeed with single-expert outputs and refusal signals differ from routing patterns.
-
ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
ImpRIF improves LLM complex instruction following by synthesizing data from reasoning graphs and training models to reason explicitly along those graphs.
-
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
Retrieval-of-Thought organizes prior reasoning into a thought graph for retrieval and reward-guided recombination, reducing output tokens by up to 40% and latency by 82% while preserving accuracy on reasoning benchmarks.
-
Learning to Reason under Off-Policy Guidance
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.
-
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.