ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Paper • 2608.05102 • Published • 62
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 18 hours ago
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment updated a collection about 18 hours ago
WTF GENIUS PAPERS upvoted a paper about 18 hours ago
Lossless Tensor Compression as Program SynthesisOrganizations
upvoted 6
papers about 18 hours ago
Lossless Tensor Compression as Program Synthesis
Paper • 2608.02162 • Published • 11
MameLoshnLM: Yiddish Language Model and Evaluation Benchmark
Paper • 2608.05850 • Published • 14
On-Policy Delta Distillation for Multilingual Math Reasoning
Paper • 2608.05802 • Published • 23
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Paper • 2608.06352 • Published • 15
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 74
upvoted 5
papers 1 day ago
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Paper • 2607.28048 • Published • 10
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Paper • 2607.00482 • Published • 7
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
Paper • 2608.02703 • Published • 6
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Paper • 2608.00782 • Published • 15
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Paper • 2608.05139 • Published • 25
upvoted a paper 2 days ago
upvoted 5
papers 3 days ago
RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
Paper • 2608.01247 • Published • 11
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
Paper • 2608.03457 • Published • 30
MemSFT: Mitigating Alignment Tax with an External Parametric Memory
Paper • 2607.25614 • Published • 23
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
Paper • 2608.01837 • Published • 38
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Paper • 2608.04007 • Published • 18
upvoted 3
papers 4 days ago
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Paper • 2607.29377 • Published • 11
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 30
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Paper • 2608.02585 • Published • 24