UnitBoost proposes a non‑generative merge operator to manage compound LLM systems, replacing the opaque higher‑level LLM that traditionally coordinates worker outputs. The operator maps worker outputs to slot‑value proposals, uses a constrained argmax to assemble the final answer, and explicitly tracks unfilled slots as residuals for subsequent rounds, thereby achieving order‑free processing and unit provenance. Across three held‑out benchmarks, UnitBoost outperforms both gold‑label‑selected candidates and input‑matched generative managers, improving compound‑system performance by up to 0.182 points and raising FanOutQA cell F1 from 0.4778 to 0.5524.
arXiv:2606. 16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness.
The study evaluates how to best split tasks among large‑language‑model agents for cross‑border VAT determination, comparing one broad agent to configurations ranging from one to five narrow agents. Across 4,400 runs—including token‑matched and failure‑injection scenarios—the intermediate configurations achieved the highest accuracy but did not surpass the fine‑endpoint benchmark, leaving the optimal decomposition hypothesis unconfirmed. The pilot provides a preregistered heuristic for right‑sizing decomposition, along with an oracle, dataset, and analysis pipeline.
arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
arXiv:2608. 04611v1 Announce Type: cross Abstract: Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software.
arXiv:2608. 11318v1 Announce Type: cross Abstract: Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent.
SiLR introduces a structure‑preserving admission and process reward mechanism for large language model (LLM) tool agents. Unlike traditional scalar‑score gates that can trap agents in plateau trajectories, SiLR shadow‑executes each proposal and admits it based on a product order over branch‑level violation states, ensuring safe and recoverable actions. Experiments on Gym‑ANM and CityLearn benchmarks show SiLR consistently recovers all multi‑action episodes and outperforms scalar gates, while also providing a robust reward signal for policy learning.
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state h...
arXiv:2607. 17240v1 Announce Type: new Abstract: When does a committed intermediate stage in an LLM reasoning pipeline earn its cost?
arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.
arXiv:2609.24194v1 Announce Type: new Abstract: Evaluation scores used around LLM systems -- including reward models, rerankers, and LLM judges -- can track surface form instead of the quality they c...
arXiv:2607. 18553v1 Announce Type: cross Abstract: Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes?