Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
Reflect, retry, reward: Self-improving llms via reinforcement learning.CoRR, abs/2505.24726
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a model's ability to solve complex, verifiable tasks can be enhanced even when generating synthetic data is infeasible and only binary feedback is available. Our framework operates in two stages: first, upon failing a given task, the model generates a self-reflective commentary analyzing its previous attempt; second, the model is given another attempt at the task with the self-reflection in context. If the subsequent attempt succeeds, the tokens generated during the self-reflection phase are rewarded. Our experimental results show substantial performance gains across a variety of model architectures, as high as 34.7% improvement at math equation writing and 18.1% improvement at function calling. Notably, smaller fine-tuned models (1.5 billion to 7 billion parameters) outperform models in the same family that are 10 times larger. Our novel paradigm is thus an exciting pathway to more useful and reliable language models that can self-improve on challenging tasks with limited external feedback.
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
MarsTSC is a VLM agentic system with generator, reflector, and modifier roles that iteratively refines a knowledge bank to improve few-shot multimodal time series classification and produce human-readable explanations.
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
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.
Adding controlled noise and irrelevant persona contexts across training and testing stages for strong LLMs yields better reasoning and efficiency than high-quality data alone, reaching 76.7% on AIME24/25 with Qwen2.5-32B.
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
citing papers explorer
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
-
Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning
MarsTSC is a VLM agentic system with generator, reflector, and modifier roles that iteratively refines a knowledge bank to improve few-shot multimodal time series classification and produce human-readable explanations.
-
AIPO: Learning to Reason from Active Interaction
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
-
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.
-
Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency
Adding controlled noise and irrelevant persona contexts across training and testing stages for strong LLMs yields better reasoning and efficiency than high-quality data alone, reaching 76.7% on AIME24/25 with Qwen2.5-32B.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.