15 papers
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Chunyang Jiang, Pingping Zhang, Yuzhi Zhao +9
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimod…
SoftSkill: Behavioral Compression for Contextual Adaptation
Xijia Tao, Yihua Teng, Xinyu Fu +6
Agent skills are commonly deployed as natural-language Markdown files that encode answer policies, evidence-use habits, and task procedures. These files are readable and portable,…
Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
Senkang Hu, Yong Dai, Yuzhi Zhao +5
Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, but yet optimizing the retrieval process remains challenging due to the lack of d…
Unified Context Evolution for LLM Agents
Zixuan Zhu, Yitong Hu, Yong Dai +4
LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed context and any useful strateg…
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
Jiazhen Huang, Xiao Chen, Xiao Luo +3
On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Exist…
Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
Senkang Hu, Yong Dai, Xudong Han +4
Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards requir…