News without the noise
Benchmark
Reported in 65 papers on Zotpaper. The latest, each as the paper states it:
30 results for “ALFWorld” · 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.
ALFWorld: 77.7% pooled success rate (as reported)
The Chinese University of Hong Kong, Tencent, Peking University
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.
ALFWorld: 91.54% Out-Success (as reported)
Beihang University, Alibaba Group
Research · Agents
RLiD: Reinforcement Learning in the Decision Plane for Language Agents and LLMs
On a household-task benchmark, training a model to choose directly among labelled actions reached 99.3% success in 12.7 GPU-hours, where token-level reinforcement learning reached 86.6% in 17.3.
ALFWorld: 99.3% success (as reported)
University of Illinois Urbana-Champaign, National University of Singapore, Zhejiang University
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.
ALFWorld: 99.3% success rate (as reported)
Microsoft AI
Research · Reinforcement learning
Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
HP-RLVR uses a trajectory’s realized future and verifier feedback to weight token updates without group sampling, reference answers or a learned critic.
ALFWorld: 2.3 x training speedup (as reported)
South China University of Technology, Tsinghua University, The Hong Kong University of Science and Technology
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.
ALFWorld: 96.9% success rate (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.
ALFWorld: 91.9% success rate (as reported)
University of Science and Technology of China, Zhongguancun Academy, Shandong University
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.
ALFWorld: 13.83 pts mean success gain over Vanilla OPD (as reported)
Tsinghua University, SenseTime Research, Peking University
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.
ALFWorld: 91.9% success rate (as reported)
Zhejiang University, Westlake University, Westlake Institute for Advanced Study
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.
ALFWorld: 95.3% success rate (as reported)
City University of Hong Kong, Tencent, Nanjing University
Research · Agents
Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
Zhong et al. show that on-policy distillation repairs weak student decisions early but erodes successful ones later, and propose SPOD to protect them.
ALFWorld: 88.9% success (as reported)
University of Southern California, University of Florida, Emory University
Research · Language models
DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
DTDD uses segment-level divergence to switch from on-policy distillation to teacher-generated recovery, improving stability and sample efficiency across reasoning and agentic tasks.
ALFWorld: 81.32% average success (as reported)
Google, University of Washington, Boston University
Research · Agents
Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
TJPO rewards task-specific variation across groups of trajectories while preserving competitive success rates.
ALFWorld: 0.91 Success (as reported)
Microsoft, tuyoogame
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.
ALFWorld: 95.7% success rate (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.
ALFWorld: 91% success rate (as reported)
Alibaba Group, Kyoto University, NII LLMC
Research · Agents
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
ASCENT enables online test-time training of LLM agents by self-distilling successful trajectories into persistent weight updates without external supervision.
ALFWorld: 90% success rate (as reported)
University of New South Wales (UNSW Sydney)
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.
ALFWorld: 74.7% overall success rate (as reported)
Nanjing University, ByteDance
Research · Reinforcement learning
Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning
CRBC recursively combines evidence from intersecting rollouts while weighting alternative actions and transitions by their observed frequencies.
ALFWorld: 5.59 pts overall success rate improvement over strongest baseline (as reported)
Beihang University, Zhongguancun Academy, Communication University of China
Research · Reinforcement learning
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
PivotOPD identifies consequential mistakes in student rollouts, then distills both the preferred action and subsequent recovery behavior.
ALFWorld: 5.5% improvement over strongest baseline (as reported)
Princeton University, NVIDIA, University of Maryland
Research · Reinforcement learning
From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
A teacher-guided warmup improved early reward discovery and subsequent reinforcement learning in interactive agent tasks.
ALFWorld: 96.7% success (pass@1) (as reported)
Zhejiang University, Ant Healthcare, Ant Group