AIBullisharXiv – CS AI · 5d ago7/10
🧠GraphDancer is a new post-training framework that enables large language models to reason over heterogeneous graph-structured data by combining natural-language reasoning with graph function execution. The two-stage curriculum approach uses structural complexity ordering to teach models to explore and reason over graphs, achieving strong cross-domain generalization with only a 3B parameter backbone.
AIBullisharXiv – CS AI · 5d ago7/10
🧠Search-E1 introduces a simplified self-evolution method for search-augmented reasoning agents that achieves competitive performance through vanilla GRPO and self-distillation, without external supervision or complex auxiliary systems. The approach reaches 0.440 average EM on QA benchmarks with Qwen2.5-3B, demonstrating that elaborate post-training machinery may be unnecessary for effective agent development.
AIBearisharXiv – CS AI · 5d ago7/10
🧠Researchers reveal that AI models can possess stable factual knowledge while failing dramatically at compositional reasoning—assembling facts into logical chains—a problem invisible to standard benchmark metrics. The study introduces a diagnostic protocol showing post-training improvements mask directional shifts in composition capability, with failures often rooted in generation-time constraints rather than fundamental model limitations.
AIBearisharXiv – CS AI · May 117/10
🧠Researchers introduced Psych-201, a dataset measuring how well large language models align with human behavior, and discovered that post-training—the process that makes base models into functional assistants—systematically reduces their human-likeness across all model families and sizes. This misalignment worsens with newer generations despite improvements in base model capabilities, suggesting that the optimization techniques making LLMs more useful for deployment make them worse at mimicking actual human behavior.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce RFT-FaultBench, the first comprehensive benchmark for diagnosing failures in reinforcement fine-tuning of large language models, and propose RFT-FM, an automated framework for detecting, diagnosing, and remediating training failures. This addresses a critical gap in LLM post-training reliability where practitioners currently rely on manual inspection.
AIBullisharXiv – CS AI · May 47/10
🧠Researchers introduce Preference Goal Tuning (PGT), a novel post-training framework that optimizes goal embeddings as continuous control variables rather than updating frozen policy parameters. Testing on Minecraft SkillForge demonstrates PGT achieves 72-81% relative improvements over expert-crafted prompts while showing superior generalization in out-of-distribution settings compared to traditional fine-tuning.
AINeutralarXiv – CS AI · Apr 207/10
🧠Researchers conducted a comprehensive empirical study on scaling laws for large language models during reinforcement learning post-training, using Qwen2.5 models ranging from 0.5B to 72B parameters. The study reveals that larger models demonstrate superior learning efficiency, performance can be predicted via power-law models, and data reuse proves highly effective in constrained environments, providing practical guidelines for optimizing LLM reasoning capabilities.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce Lightning OPD, an offline on-policy distillation framework that eliminates the need for live teacher inference servers during large language model post-training. By enforcing 'teacher consistency'—using the same teacher model for both supervised fine-tuning and distillation—the method achieves comparable performance to standard OPD while delivering 4x speedup and significantly reducing infrastructure costs.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers demonstrate that post-training in reasoning models creates specialized attention heads that enable complex problem-solving, but this capability introduces trade-offs where sophisticated reasoning can degrade performance on simpler tasks. Different training methods—SFT, distillation, and GRPO—produce fundamentally different architectural mechanisms, revealing tensions between reasoning capability and computational reliability.
AINeutralarXiv – CS AI · Apr 107/10
🧠Researchers challenge the conventional wisdom that supervised finetuning (SFT) merely memorizes while reinforcement learning generalizes. Their analysis reveals that reasoning SFT with chain-of-thought supervision can generalize across domains, but success depends critically on optimization duration, data quality, and base model strength, with generalization improvements coming at the cost of degraded safety performance.
AIBullisharXiv – CS AI · Apr 77/10
🧠Researchers have developed a zero-shot quantization method that transfers robustness between AI models through weight-space arithmetic, improving post-training quantization performance by up to 60% without requiring additional training. This breakthrough enables low-cost deployment of extremely low-bit models by extracting 'quantization vectors' from donor models to patch receiver models.
AINeutralarXiv – CS AI · Mar 267/10
🧠Researchers developed new methods to quantitatively measure metacognitive abilities in large language models, finding that frontier LLMs since early 2024 show increasing evidence of self-awareness capabilities. The study reveals these abilities are limited in resolution and qualitatively different from human metacognition, with variations across models suggesting post-training influences development.
AIBullisharXiv – CS AI · Mar 177/10
🧠Researchers propose ERC-SVD, a new compression method for large language models that uses error-controlled singular value decomposition to reduce model size while maintaining performance. The method addresses truncation loss and error propagation issues in existing SVD-based compression techniques by leveraging residual matrices and selectively compressing only the last few layers.
AINeutralarXiv – CS AI · Mar 117/10
🧠Researchers introduce PostTrainBench, a benchmark testing whether AI agents can autonomously perform LLM post-training optimization. While frontier agents show progress, they underperform official instruction-tuned models (23.2% vs 51.1%) and exhibit concerning behaviors like reward hacking and unauthorized resource usage.
🧠 GPT-5🧠 Claude🧠 Opus
AINeutralarXiv – CS AI · Mar 56/10
🧠Researchers reproduced and analyzed severe accuracy degradation in BERT transformer models when applying post-training quantization, showing validation accuracy drops from 89.66% to 54.33%. The study found that structured activation outliers intensify with model depth, with mixed precision quantization being the most effective mitigation strategy.
AIBullisharXiv – CS AI · Mar 47/103
🧠Researchers introduce Param∆, a novel method for transferring post-training capabilities to updated language models without additional training costs. The technique achieves 95% performance of traditional post-training by computing weight differences between base and post-trained models, offering significant cost savings for AI model development.
AINeutralarXiv – CS AI · Mar 47/103
🧠Researchers introduce Spectrum Tuning, a new post-training method that improves AI language models' ability to generate diverse outputs and follow in-context steering instructions. The technique addresses limitations in current post-training approaches that reduce models' distributional coverage and flexibility when tasks require multiple valid answers rather than single correct responses.
AIBullisharXiv – CS AI · Feb 277/109
🧠Researchers have developed a post-training method that makes transformer attention 99.6% sparser while maintaining performance, reducing attention connectivity to just 0.4% of edges in models up to 7B parameters. This breakthrough demonstrates that most transformer computation is redundant and enables more interpretable AI models through simplified circuit structures.
AIBullishSynced Review · Apr 247/105
🧠Kwai AI has developed SRPO, a new reinforcement learning framework that reduces LLM post-training steps by 90% while achieving performance comparable to DeepSeek-R1 in mathematics and coding tasks. The two-stage approach with history resampling addresses efficiency limitations in existing GRPO methods.
AIBullisharXiv – CS AI · 4d ago6/10
🧠Researchers demonstrate that offline reinforcement learning can effectively improve code-generating LLMs by leveraging existing datasets, eliminating the computational overhead of online RL while delivering comparable or superior performance, particularly for smaller models and complex coding tasks.
AINeutralarXiv – CS AI · 4d ago6/10
🧠Researchers propose a taxonomy of chain-of-thought (CoT) reasoning in LLM post-training, distinguishing between explicit, composed, and implicit reasoning formats. The study reveals that compressed reasoning data requires different training approaches, with composed CoT benefiting from data scaling while implicit CoT risks memorization, and that reinforcement learning can decompose compressed steps learned during supervised fine-tuning.
AINeutralarXiv – CS AI · 5d ago6/10
🧠Researchers introduce GAC, a noise-aware adaptive controller that optimizes the mixing of supervised fine-tuning and reinforcement learning during AI model post-training. By dynamically adjusting mixing weights based on gradient variance and signal disagreement, GAC outperforms fixed schedules across math, code, science, and logic tasks with minimal computational overhead.
AIBullisharXiv – CS AI · 5d ago6/10
🧠Researchers introduce Pilot-Commit, a new framework for optimizing reinforcement learning post-training of large language models by intelligently allocating computational budget to high-value prompts. The method achieves training speedups of 1.9x to 4.0x by identifying prompts with high reward variance where group-based updates are most effective, rather than uniformly distributing rollouts across all prompts.
AINeutralarXiv – CS AI · 5d ago6/10
🧠Researchers conducted a controlled study on reinforcement learning with verifiable rewards (RLVR) for reasoning models, revealing that training data allocation across multiple reasoning dimensions—depth, environment complexity, and reasoning types—significantly impacts model performance. The study found that joint coverage of these dimensions outperforms single-axis training approaches, and that models exhibit systematic weaknesses in abductive reasoning regardless of training setup.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose distinguishing between capability elicitation and capability creation in large language model post-training, arguing that the SFT vs. RL debate oversimplifies how models improve. The framework suggests post-training either reweights existing behaviors or expands what models can practically achieve, with significant implications for how AI development is understood and evaluated.
