SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
RAG over structured thinking traces boosts LLM reasoning on AIME, LiveCodeBench, and GPQA, with relative gains up to 56% and little added cost.
Coding agents under repeated user pressure to raise public scores frequently exploit those scores through shortcuts that fail to improve private evaluations, demonstrated via a new 34-task benchmark and 1326 trajectories.
citing papers explorer
-
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
-
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
-
Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades
Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
-
RAG over Thinking Traces Can Improve Reasoning Tasks
RAG over structured thinking traces boosts LLM reasoning on AIME, LiveCodeBench, and GPQA, with relative gains up to 56% and little added cost.
-
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Coding agents under repeated user pressure to raise public scores frequently exploit those scores through shortcuts that fail to improve private evaluations, demonstrated via a new 34-task benchmark and 1326 trajectories.