CIRCE is a method that estimates the difficulty of a task for a large language model (LLM) by extracting the problem’s constraint structure into a Constraint Intermediate Representation, which is then compiled into a constraint graph. Unlike prior approaches that rely on the problem text or model outputs, CIRCE uses a lightweight LLM to build this representation and feeds it to a graph neural network to predict whether the LLM will solve the problem correctly. Experiments on seven reasoning benchmarks and four LLMs show that even a randomly initialized GNN improves prediction accuracy, lowering negative log‑likelihood from 0.465 to 0.423 and raising AUROC from 0.691 to 0.727 compared to the best baseline.
Estimating whether a problem is too complex for a large language model (LLM) before the model attempts it can guide model routing, how to allocate test-time compute, and suggest the need for new tools...
RECAST is a new framework that generates datasets with far more constraints per example than existing benchmarks, aiming to push large language models (LLMs) to better follow complex instructions. The authors built RECAST-30K, a 30,000‑instance dataset covering 19 constraint types extracted from real prompt‑response pairs, and showed that fine‑tuning on it improves LLMs’ ability to handle complex tasks without harming general performance. RECAST also provides rule‑based and LLM‑based validators for automatic constraint verification, enabling reward‑based reinforcement learning to further enhance model performance on challenging tasks.
arXiv:2606. 03624v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously.
arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.
arXiv:2509. 00930v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general reasoning, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve these abilities.
arXiv:2606. 04816v1 Announce Type: new Abstract: Large language models (LLMs) increasingly translate natural-language optimization problems into executable solver code.
arXiv:2601. 09097v3 Announce Type: replace Abstract: Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints.
arXiv:2608. 02641v1 Announce Type: cross Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittle: schema, indexing, and semantic errors can cause compilation failures, infeasible models, or incorrect objectives, while iterative repair, search, and multi-agent workflows increase inference cost.
arXiv:2606. 07108v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking".
The paper investigates whether constrained decoding harms or helps large language model (LLM) performance. It introduces a taxonomy of three constraint types—format, validity, and reasoning—and shows that suitable constraints can preserve or even improve performance by eliminating invalid paths. Experiments across multiple model families reveal that perceived performance drops are mainly due to non-equivalent prompting and output formats, while validity constraints boost reliability and reasoning constraints can enhance accuracy when they guide beneficial reasoning trajectories.
arXiv:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP).