Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models

Chengxuan Pei; Ziyao Wang; Teng Mei; Zhe Li

Home/Archive/arXiv

arXiv · 2610.36595

Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models

Chengxuan Pei·Ziyao Wang·Teng Mei·Zhe Li

View original source ↗Read source document ↗Export metadata ↓

Abstract

Decision models offer fast choices over sup- plied alternatives, while general-purpose large language models interpret open-ended tasks through flexible generation and reasoning at the cost of sequential decoding. Many work- loads expect a generative backend to determine what can be done and therefore provide no well-defined candidate list. We bridge this in- terface gap with a small candidate formalizer trained on offline teacher-generated lists. The formalizer constructs explicit, validated alter- natives from task context, and a frozen deci- sion model selects an entry. A motivating com- parison with official TypeSafe Jev-1.13.0 on 200 CALVIN-D test episodes reports 11% suc- cess with generic motions versus 46.5% with DeepSeek V4 Flash pose candidates. Sepa- rately, a six-arm privileged-state evaluation on 1,011 CALVIN-D validation annotations finds that a locally deployed decision model can achieve at most 52.6% task success rate with the fine-tuned formalizer, compared with 11.8% without it, and the end-to-end latency is kept to 2.09 s, whereas Qwen3.5-27B is 3.67 s with the exact experiment setting.

Explore related subjects

cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Chengxuan Pei, Ziyao Wang, Teng Mei, Zhe Li. 2026-10-27. Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models. https://arxiv.org/abs/2610.36595

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Epsilon-Identifiability of Causal Quantities

Identifying the effects of causes and causes of effects is vital in virtually every scientific field. Often, however, the needed probabilities may not be fully identifiable from the available data sources. This paper shows how approximate identifiability is still possible for several probabilities of causation. We term this epsilon-identifiability and demonstrate its usefulness in cases where the behavior of certain subpopulations can be restricted within sufficiently narrow bounds. In particular, we show how unidentifiable causal effects and counterfactual probabilities can be epsilon-identified when such allowances are made. Often, these allowances are easily measured and reasonably assumed. Finally, epsilon-identifiability is applied to the unit selection problem.

cs.AI↗

arXiv2026

PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement

Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve Trajectories) addresses this plan-execution misalignment through a self-supervised framework that treats trajectories as optimizable objects iteratively refined via environment interaction. The framework comprises four stages: PLAN generates candidate trajectories; INSPECT executes them and computes structured losses with textual gradients encoding plan-execution discrepancies; EVOLVE applies these signals to produce improved trajectories; and VERIFY performs a final global check against task constraints. A monotonic acceptance process ensures a non-decreasing solution quality. Empirical evaluations on DeepPlanning and GAIA demonstrate state-of-the-art performance: with human-in-the-loop (HITL) feedback, PIVOT establishes a strong upper bound up to 94% relative improvement in constraint satisfaction, while its fully autonomous variant retains substantial gains, showing that the core trajectory-refinement mechanism remains effective without external supervision. At the same time, PIVOT remains computationally efficient, requiring up to 3x to 5x fewer tokens than competing refinement methods. These findings establish that (self- or human-supervised) feedback-based trajectory optimization is a principled methodology for mitigating plan-execution gaps in autonomous agent systems.

cs.AI↗

arXiv2026

Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning

Modern AI agents are increasingly capable of routine financial-analysis tasks such as retrieving documents and updating spreadsheets. A harder challenge is forecasting an unknown future from incomplete information. Public markets provide a natural testbed: analysts routinely predict discrete events with information from that point in time. We present Hedge-Bench, a benchmark of 92 real-world environments derived from hedge fund analysts' reasoning traces paired with subsequently resolved prediction questions. Agents reason from frozen information snapshots, and their forecasts are evaluated against real-world outcomes. Across 11 frontier models and three trials per environment, joint success rates, which require both a correct forecast and over 60% research coverage, range from 2.54 to 31.52%. Using GRPO with turn-level credit assignment, we train Muse-Glimmer on 165 environments, increasing coverage on 22 held-out environments from 17.17% to 33.36% at low reasoning effort and from 30.19% to 47.02% at extra-high effort. The trained model at low effort also exceeds the base model's extra-high-effort coverage while using 47.9% fewer tokens. We also observe evidence of generalization: held-out forecasting accuracy at high effort improves by 10.06 percentage points, while out-of-distribution evaluation scores improve by 3.94 points on GDPval, 2.29 on GDP.pdf, 7.07 on Harvey LAB, and 4.96 on Frontier Finance under their respective metrics. Code: https://github.com/Trata-Inc/trata-hedge-bench-verified.

cs.AI↗