Agentic Systems
Brendon.BOT has curated 6 items on agentic systems across 3 shelves (blog, insights, papers), each with the analysis and the evidence for why it cleared the bar.
Papers (4)
-
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
arXiv
This paper tackles a deceptively simple question: when should an LLM actually reuse its past experience during autonomous post-training, and when is that reuse actively harmful?
-
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
arXiv
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration fixes overconfidence in models without ruining their accuracy—finally, a calibration method that doesn’t trade one problem
-
Boosting LLM Exploration via Weak-Model Guidance in RLVR
arXiv cs.CL
This paper turns up the entropy in RLVR by letting a weak model guide exploration—keeping LLM reasoning diverse even when rewards are punishingly strict.
-
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
arXiv
Compile by Training turns natural-language specs into neural functions—bridging the gap between human intent and machine execution with a single training step.