News without the noise
Benchmark
Reported in 43 papers on Zotpaper. The latest, each as the paper states it:
39 results for “WebShop” · page 1 of 2
Research · Agents
CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
CORD selectively removes opposing gradient components while preserving a protected objective, boosting task success on ALFWorld and WebShop across several training recipes.
WebShop: 64.5% success rate (as reported)
The Chinese University of Hong Kong, Tencent, Peking University
Research · Agents
SAPD: Learning from Agent Experience without Environment Interaction
SAPD decomposes recorded multi-turn histories into decision prefixes and uses relative step advantages to stabilize policy distillation, improving results on ALFWorld, WebShop and Search-based QA.
WebShop: 10.9 x per-step training time speedup vs online OPD (as reported)
Meituan, University of Chinese Academy of Sciences
Research · Agents
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
The authors compile 50,228 diagnosed failures and show that proposed corrections often outperform retrying the original action.
WebShop-lite: 6.67 pts task success gain vs success-only training (as reported)
Apodex
Research · Reinforcement learning
BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents
Across two simulated environments and two model sizes, the authors report higher task success when training reuses evidence about useful actions across tasks and training updates.
WebShop: 79.43% Task Success (as reported)
Beihang University, Alibaba Group
Research · Agents
TalentRL: Strategy-Guided Reinforcement Learning for Hierarchical Skill Routing
A hierarchical reinforcement learning approach separates strategy selection from skill execution to improve routing credit assignment.
WebShop: 90.7 average score (as reported)
Microsoft AI
Research · Evaluation & benchmarks
IntentDelta: A Human-Constructed Benchmark for Evolving User Intent
A human-constructed benchmark tests eleven agents on shopping and travel tasks, finding weaknesses in both recovering revised intentions and executing them.
WebShop: 52% Intention Recovery (as reported)
Georgia Institute of Technology, Microsoft Research
Research · Reinforcement learning
Contextual Credit Policy Optimization
CCPO uses context-weighted trajectory comparisons and short-horizon progress to identify which actions contributed to eventual success.
WebShop: 85.4 mean task score (as reported)
Stanford University, Texas A&M University, Yale University
Research · Agents
VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents
VETTA learns both credit types via separate value heads on a lightweight shared critic, improving success rates on two agent benchmarks.
WebShop: 86.5 task score (as reported)
University of Science and Technology of China, Zhongguancun Academy, Shandong University
Research · Reinforcement learning
TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
TrajEvolve revises unnecessary steps in historical trajectories and uses the resulting paths alongside fresh policy rollouts during training.
WebShop: 71.9% success rate (as reported)
City University of Hong Kong, Tencent, Nanjing University
Research · Agents
From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents
A training loop that extracts reusable sub-skills from unsuccessful web-browsing trajectories, stitches them into longer skill chains, and distils the results back into the model improved task success by 3.9% to 18.6% over the strongest baselines.
WebShop: 108729 model calls (as reported)
Renmin University of China, Huawei Technologies
Research · Language models
Branching On-Policy Distillation
Chen et al. show that resampling continuations at informative decision points broadens teacher supervision and outperforms independent rollouts with fewer student tokens.
WebShop: 33.59% success rate (as reported)
Tsinghua University, SenseTime Research, Peking University
Research · Agents
Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers
Graph-conditioned on-policy distillation scores student actions against indexed teacher executions, improving success on three agent benchmarks.
WebShop: 39.9% success rate (as reported)
Yuanbao Team, Tencent, Tsinghua University, Huazhong University of Science and Technology
Research · Reinforcement learning
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
ProAS uses a reference graph to mask invalid actions and penalize early deviations, boosting success and convergence.
WebShop: 70.8% success rate (as reported)
Zhejiang University, Westlake University, Westlake Institute for Advanced Study
Research · Agents
Learning from Interaction Experience via Localized Context Distillation
The authors propose a method that identifies and revises only critical spans in a student's trajectory, outperforming both off-policy and on-policy context distillation across math, code, and agent tasks.
WebShop: 52.4% task success rate (as reported)
Tencent, The Chinese University of Hong Kong, Zhejiang University
Research · Reinforcement learning
T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
T2SPO uses a frozen TabPFN to estimate remaining distance to success at each state, deriving auxiliary step rewards from past successful rollouts to improve policy learning.
WebShop: 88.5 task score (as reported)
Nanjing University, ByteDance
Research · Agents
Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks
Sibyl trains a 0.6-billion-parameter model to request step-level assistance only when useful, then absorb that guidance into later decisions.
WebShop: 64.8% call ratio (as reported)
Hangzhou Dianzi University, Fudan University, The Hong Kong University of Science and Technology
Research · Agents
Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
Outcome-guided weighting identifies which teacher interventions actually help the current student complete multi-turn tasks.
WebShop: 57.9 Score (as reported)
Qwen Large Model Application Team, Alibaba, Peking University, University of Chinese Academy of Sciences
Research · Reinforcement learning
GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents
GraphHCA derives step-level training signals from pooled rollout graphs without a critic, hindsight model, or additional forward pass.
WebShop: 90.5 task score (as reported)
Beihang University, Zhongguancun Academy, Communication University of China
Research · Reinforcement learning
My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning
FAULT converts verified natural-language error diagnoses into step-level training signals while preserving the trajectory’s terminal outcome.
WebShop: 88.5% task score (as reported)
Alibaba Group, Kyoto University, NII LLMC
Research · Agents
Procedural Exposure Bias in Skill-Augmented Language Model Agents
The same procedural content, shown as text versus as an image, leads to measurable differences in action preference and downstream agent success.
ALFWorld, ScienceWorld, WebShop: 53.94% macro-average success rate (as reported)
Northeastern University, Alibaba Group