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.
By Pedro Santos
arXiv:2610. 29052v1 Announce Type: cross Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logits or a small head over its hidden states, instead of generating and parsing text.
By Yuchuan Weng, Chi Liu, Xin Chen, Srinivasan Manoharan
arXiv:2608. 07952v1 Announce Type: cross Abstract: Tool-augmented LLM agents can harbor implicit state that persists across sessions, activates through events, and propagates across agent boundaries---largely invisible to standard debugging.
By Zhaohui Wang
arXiv:2607. 26448v1 Announce Type: cross Abstract: A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length grows.
By Dachuan Song, Junyu Yin, Zechen Hu, Xuan Wang
arXiv:2609.23886v1 Announce Type: new
Abstract: Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears wit...
By Zehua Cheng, Wei Dai, Jiahao Sun
arXiv:2607. 23191v2 Announce Type: replace Abstract: Fine-tuned code LLMs are often conditioned on a design-intent header to steer parametric CAD generation, but whether the model reads that header's content has been tested neither under execution-level scoring nor with a causal control.
By Yang Xiao
The paper introduces Agentic Conversation Context Curation (AC3), a training‑free method that cleans multi‑turn human‑AI dialogue by consolidating the user’s task specification, auditing assistant outputs, and editing the context to remove or rebuild assistant turns. AC3 outperforms both full context and assistant‑omission (AO) baselines on several benchmark tasks, closing a significant portion of the performance gap and receiving preference from a GPT‑5‑mini judge on real WildChat conversations. The study also shows that context pollution is contagious and that simply ignoring assistant turns can worsen performance, underscoring the need for structured removal of assistant content.
By Matthew Ho, Chenglong Wang, Baolin Peng, Nebojsa Jojic, Philippe Laban, Michel Galley, Jianfeng Gao, Lianhui Qin
arXiv:2607. 24797v1 Announce Type: cross Abstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-parietal encoding route (impaired in pure agraphia), sharing a partial orthographic core.
By Diego Salda\~na Ulloa
arXiv:2606. 00671v3 Announce Type: replace Abstract: We present Moxia (formerly AXIOM), a trust-first neuro-symbolic architecture for self-explaining mathematical reasoning over natural-language input.
By Alessio Bruno
The paper reports that agent evaluations often show a tool‑call rate of zero even when the model emits valid calls, because the interface censors the trajectory before downstream components see it. Experiments on BFCL v4 and tau‑bench demonstrate that swapping the serving adapter can change the observed call rate from 0.00 to 0.96/0.19 or from 0 to 636 calls, indicating that the interface—not the model—causes the discrepancy. A 98‑line preflight check is released to detect such silent failures, highlighting that tool‑call rates depend on the model‑interface stack rather than the model alone.
By Wenbo Wang
The paper introduces AgentDiff, a metric that quantifies how much LLM agents’ answers differ when inputs are altered by meaning‑bearing rewrites (paraphrases, synonym substitutions) versus presentation changes (reordering, formatting, distractors). Across 68 model–benchmark–scaffold combinations involving ten LLMs and over 1,500 questions, meaning‑bearing rewrites consistently produce a roughly 20‑percentage‑point higher inconsistency rate than presentation changes, a gap that persists across severity proxies and remains significant even outside the Qwen family. Trace analysis reveals that meaning‑bearing rewrites preserve the first action but reduce thought similarity from the second step onward, extending the divergence cascade—a phenomenon termed “stealth divergence.”
By Liyun Zhang, Jiayi Guo
arXiv:2607. 18476v1 Announce Type: cross Abstract: When a language model must choose one answer from a large space of equally valid options, a format clause -- "Reply with JSON only" -- changes which answer it chooses.
By Tapan Parikh