arXiv AI
Jul 29
Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT
arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.
Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation
The study investigates how inference‑time interventions and weight consolidation affect open‑ended generation in an online bin‑packing task. By iteratively generating, verifying, selecting, and consolidating with LoRA, the model’s outputs shift toward higher value, reducing excess by 1.7 points and outperforming random consolidation by 3.1 points. Across three independent runs, the mean performance remained consistent, and the best candidates converged to the classic heuristic’s level without exceeding it, while consolidation also lowered the proportion of better‑than‑classic candidates but increased their absolute number.
Related stories
arXiv AI
Jul 14
The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation
arXiv:2607. 09709v1 Announce Type: new Abstract: Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact.
arXiv AI
Aug 21
Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
arXiv:2608. 19888v1 Announce Type: cross Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer.
arXiv AI
Jun 29
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.
arXiv Machine Learning
Aug 3
ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning
arXiv:2607. 29400v1 Announce Type: new Abstract: A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions.
arXiv AI
Jul 31
One Run Is Not an Idea: The Implementation Lottery in Automated Research
arXiv:2607. 26587v1 Announce Type: cross Abstract: Automated research systems use experimental scores both to deliver artifacts and to decide which ideas to retain, transfer, and pursue.
arXiv AI
Jul 21
Teach it to stop, not just to click
arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.
arXiv AI
Jun 16
Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines
arXiv:2606. 15474v1 Announce Type: new Abstract: Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down.
arXiv AI
Jul 29
When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.
arXiv Machine Learning
Aug 13
MMLA: How Memory Lets the Past Shape the Future
arXiv:2606. 28876v3 Announce Type: replace-cross Abstract: Proposal.
arXiv AI
Aug 20
Governance Records as Supervision: Verifier-Selected Self-Training for Structured Workflow Repair
The study demonstrates that governance records—structured logs linking task contracts, model attempts, verifier decisions, and outputs—can serve as effective supervision for bounded AI models. Using a verifier-selected self‑training approach, the authors show that a Qwen3‑14B model trained on plans accepted by an independent VAL verifier achieved significant gains in plan acceptance across numerous PlanBench replanning cases, outperforming other selection strategies. The results highlight the feasibility of one‑shot execution and cumulative learning without relying on oracle targets or stronger teachers.
arXiv AI
Aug 11
DarwinX: Evolving Agent Harnesses Through Natural Selection
arXiv:2608. 07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow.