arXiv AI

FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training

FlavourBench is a new evaluation framework that replaces missing answer keys with dense reward maps generated from a versioned culinary environment. Each task requires selecting a three‑ingredient portfolio from eight options, and all 56 possible portfolios are scored by Epicure before model inference. The authors evaluate 27 endpoints across 534 tasks, perform statistical tests on 351 model contrasts, and conduct a preregistered post‑training study showing that LoRA fine‑tuning on Qwen3‑0.6B improves performance on 84 anchor‑disjoint maps by 13.30 points.

arXiv AI
6d ago

FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth

FlavourBench is an automated benchmark that evaluates language models on culinary tasks by providing a versioned, executable ground truth system. Each task presents eight ingredients and asks the model to propose a three‑ingredient portfolio, with all 56 possible portfolios scored by the Epicure system before model execution. The benchmark assesses 27 frontier endpoints across 534 tasks, yielding a FlavourBench Score that averages frozen task scores across families, and includes extensive statistical analysis and reproducible data releases.

By Josef Chen, Erim Hayretci
arXiv AI
6d ago

UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists

UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations. "whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."

By Ye Chen, Weining Zhang
arXiv AI
Aug 7

Recursive Synthesis for Long-Horizon Terminal Tasks

arXiv:2608. 05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent.

By Zhongzhi Li, Yucheng Shi, Zongxia Li, Ruhan Wang, Anhao Li, Zixun Huang, Junyao Yang, Lei Ke, Ninghao Liu, Haitao Mi, Leowei Liang
arXiv AI
2d ago

Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance

The paper evaluates a manager‑worker scaffold that uses a shared filesystem workspace to orchestrate multi‑agent large language model (LLM) coding tasks without training or tuning. Across nine models—including five open‑weight and four closed‑weight systems—the scaffold yields statistically significant accuracy gains for some models (e.g., Qwen3.8‑27B, GPT‑5.6‑Luna, GPT‑5.6‑Terra, Kimi‑K3, Minimax‑M3) while producing null or negative effects for others (e.g., Qwen3.6‑35B). The study shows that the manager can triple token usage but still achieves higher accuracy at a fraction of the cost compared to larger single‑pass models, with key mechanisms identified as context management and problem decomposition.

By Victor Gao (Sang Won), Vida Khosrowshahi (Sang Won), Ali Khosrowshahi (Sang Won), Xihao Sun (Sang Won), Juhyun Lee (Sang Won), Simon (Sang Won), Lee
arXiv AI
4d ago

Joint Optimization of Tool Creation and Use for Large Language Model Agents

The paper introduces SMITH, a reinforcement learning framework that jointly trains large language models to create and use tools within a single policy. By alternating between build and use tasks and employing separate reward signals for schema, code, and outcome failures, SMITH enables a 4B Qwen3 model to achieve state‑of‑the‑art accuracy on procedural reasoning benchmarks, outperforming larger untrained models and improving performance on downstream tasks when its tools are applied.

By Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Shao-Hua Sun, Hung-yi Lee
arXiv AI
Jun 4

Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance

arXiv:2606. 04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach.

By Kaustav Kundu, Ritvik Shrivastava, Maxim Arap, Nanshu Wang, Xianhui Zhu, Quintin Fettes, Gautam Tiwari, Parth Suresh, Th\'eo Moutakanni, Alejandro Castillejo Munoz, Allen Bolourchi, Pascale Fung, Pinar Donmez, Babak Damavandi, Anuj Kumar, Seungwhan Moon
Hugging Face Trending Papers
Jul 30

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts

Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on "cliff" prompts-those on which every sampled rollout in a group fails-the group-normalized advantage is identically zero, so GRPO produces no gradient on precisely the prompts at the frontier of the model's capability. We introduce LoRA Scaffolded Policy Optimization (LSPO), a sampling-time mechanism that recovers this lost gradient.

arXiv AI
4d ago

PROOF-Gen: From Optimized Data to Better Distillation

PROOF-Gen is a method that improves distillation of tool‑calling models by recovering successful trajectories from teacher failures. It uses per‑scenario prompt optimization to generate corrective guidance that steers the teacher to a passing trajectory, then removes this guidance before training so the student learns from clean demonstrations. On τ2‑bench, PROOF-Gen recovers 93% of failed scenarios, boosting Qwen3‑4B‑Instruct‑2507’s Pass^1 from 0.132 to 0.529 and improving Gemma 4 E4B‑it by 7.2pp on BFCL v4 multi‑turn, while also raising deployed on‑device model performance by up to 5.0pp across response‑quality metrics.

By Anh Ta, Junjie Zhu, Shahin Shayandeh
arXiv AI
Jul 15

A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

arXiv:2607. 12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent.

By Chengguang Gan, Zhixi Cai, Yunhao Liang, Hanjun Wei, Shiwen Ni, Qinghao Zhang