arXiv:2611.18538v1 Announce Type: cross
Abstract: An information system often has to learn before it knows what it will be asked. A finite representation can succeed without recording an infinite env...
By Mojtaba Soltanalian
arXiv:2606. 12502v1 Announce Type: cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same category as information.
By Cheng Qian
The paper investigates how users should set the reasoning‑effort level in large language models, a parameter that trades off inference cost for potential performance gains. Experiments on proprietary and open‑weight models across four benchmarks show that higher effort does not consistently improve accuracy, can be up to 42× more expensive on easy tasks, and alters agent behavior by increasing verification and search steps. The authors propose a simple escalation strategy—starting at the lowest effort and only increasing after a verified failure—that matches or outperforms fixed high‑effort settings while reducing cost.
By Kaiser Sun, Yongchan Kwon, Zain Hasan, Shang Zhu, Kaitlyn Zhou, Federico Bianchi
The paper investigates when reallocating a fixed test‑time budget toward harder instances improves solution quality for neural combinatorial optimization solvers. Through pre‑registered experiments on three solvers and two hard‑workload constructions for the traveling salesman problem, it finds that the key deciding factor is the variation in instance difficulty within a workload, not the average difficulty. A budget‑aware policy that first spends part of the budget to gauge instance difficulty recovers most of the potential improvement, though not all, when the cost of this information is included.
By Jinhyung Bae
arXiv:2610.08884v1 Announce Type: cross
Abstract: A declared task can sometimes certify a reduced source before a downstream encoder, codebook, rate, distortion target, or optimizer is chosen. This p...
By Joss Armstrong
arXiv:2609.00378v1 Announce Type: new
Abstract: Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadrat...
By Madhulatha Mandarapu, Sandeep Kunkunuru
Verdict-MQ is an open encoder that processes a single piece of state once and then answers multiple typed questions about that state, avoiding separate passes for each question. By using a structured attention mask, it ensures the state encoding is independent of question order and prevents questions from influencing one another. On the typed‑decisions benchmark, Verdict‑MQ outperforms a larger specialist model, achieving higher accuracy and better calibration, while on other benchmarks it shows mixed results compared to fine‑tuned baselines.
By Avdhesh Singh Chouhan, Jack Perry
The paper reports on a deployed multi‑agent tender‑response system that uses an open‑weights language model under sovereignty constraints. In a blind comparison, the system’s answers were judged at least as good as human‑written bids in 40 of 55 sections, with only a few gaps attributable to missing knowledge rather than writing quality. The study also demonstrates an asymmetry in conditioning: while structural markup improves reading tasks, converting instruction material from prose to nested XML degrades answer quality, and naming forbidden constructions concentrates defects.
By Cheng Yu, Nikhil Mathew, Zhengjie Wang
arXiv:2606. 09858v1 Announce Type: cross Abstract: Robust decision-making requires compression.
By Mark Walsh
arXiv:2609. 29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty.
By Yezhou Cheng, Runjia Du, Zeming Liu, Qibai Chen, Hang Lyu, Yilan Wei, Yankai Zeng, Bojun Lin
The paper investigates how to allocate a fixed number of attempts by a large language model (LLM) across inputs of varying difficulty. It finds that the optimal static allocation follows an inverted‑U shape, giving few attempts to very hard inputs and more to moderately difficult ones, and that this allocation is largely determined by prior knowledge of solvability rather than the policy itself. Using a verifier and a prior derived from a related model’s past runs, Thompson Sampling can significantly increase the solved share on the hardest workloads, whereas simple round‑robin or other tested policies fail to outperform it without such priors.
By Jinhyung Bae
Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$, where each path costs at most $K$ responses or episodes.