DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
Paper • 2609.00768 • Published • 22
🔄 In a Training Loop
Pratyay Banerjee
Neilblaze
AI & ML interests
IR, NLP, Pattern Recognition, xAI, Interpretability, Evals
Recent Activity
upvoted a paper about 8 hours ago
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory upvoted a paper about 8 hours ago
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents upvoted a paper about 8 hours ago
Steering Geometry: Validating Human Value Geometry in LLM Steering SpaceOrganizations
upvoted 18
papers about 8 hours ago
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Paper • 2609.09153 • Published • 23
Steering Geometry: Validating Human Value Geometry in LLM Steering Space
Paper • 2609.06289 • Published • 27
Evaluating the Hidden Costs of Personalization in Large Language Models
Paper • 2608.28833 • Published • 30
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Paper • 2609.04971 • Published • 32
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Paper • 2608.30468 • Published • 37
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 39
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Paper • 2609.02783 • Published • 118
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Paper • 2609.04010 • Published • 134
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Paper • 2609.03430 • Published • 175
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Paper • 2608.26730 • Published • 153
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 262
Aspire: Can Models Self-Evolve from Vague Goals?
Paper • 2608.31111 • Published • 227
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 291
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 378
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Paper • 2609.08183 • Published • 382
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 485
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 538
liked a
model about 19 hours ago
liked a
Space 5 days ago