LongAct benchmark evaluates long-horizon household task execution from free-form instructions; HoloMind agent raises performance but top VLMs still reach only 59% goal completion and 16% full-task success.
super hub Mixed citations
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Mixed citation behavior. Most common role is background (52%).
111
Pith papers citing it
18.2k
external citations · Pith
Background
52% of classified citations
abstract
Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a muscle. Once we see the kitchen in question, we can update our abstract plans to fit the scene. Embodied agents require the same abilities, but existing work does not yet provide the infrastructure necessary for both reasoning abstractly and executing concretely. We address this limitation by introducing ALFWorld, a simulator that enables agents to learn abstract, text based policies in TextWorld (C\^ot\'e et al., 2018) and then execute goals from the ALFRED benchmark (Shridhar et al., 2020) in a rich visual environment. ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions. In turn, as we demonstrate empirically, this fosters better agent generalization than training only in the visually grounded environment. BUTLER's simple, modular design factors the problem to allow researchers to focus on models for improving every piece of the pipeline (language understanding, planning, navigation, and visual scene understanding).
hub tools
citation-role summary
background 12
dataset 8
method 2
baseline 1
citation-polarity summary
claims ledger
- abstract Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a muscle. Once we see the kitchen in question, we can update our abstract plans to fit the scene. Embodied agents require the same abilities, but existing work does not yet provide the infrastructure necessary for both reasoning abstractly and executing concretely. We address this limitation by introducing ALFWorld, a simulator that enables agents to learn abstr
authors
co-cited works
representative citing papers
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
TRACE is a two-channel, distortion-free agent watermark whose selection and tally layers jointly resist deletion and rewriting by a log-holding reseller.
On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
UCOB uses local return comparisons between skill and no-skill views to choose which view teaches the other, improving agent training on ALFWorld and WebShop.
BiPACE improves LLM agent policy optimization by using bisimulation proxies from hidden states for step clustering and action-conditioned baselines for advantage estimation, raising success rates on ALFWorld, WebShop, and TextCraft.
AAWM builds training targets for world models by retrieving and synthesizing transition evidence based on the policy's self-identified decision needs at each state.
Replay pairing shows LLM agents do not persist plans in hidden states but rely on plans remaining in context, with rapid signal decay and task performance drops when plans are evicted.
SAGE-OPD improves multi-turn OPD via turn-level selective intervention, teacher-confidence weighting, and loss normalization, reporting up to 13.3% relative gain in ALFWorld unseen success rate over standard OPD.
StaminaBench evaluates coding agents over 100 procedurally generated change requests to a REST API, finding that tested models fail within 5-6 turns without feedback but improve up to 12x with test feedback and good harnesses.
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
SMAC-Talk is a new benchmark that adds natural language messaging and deceptive-agent scenarios to SMAC for testing LLM coordination in multi-agent environments.
ElasticMem enables LLM agents to learn adaptive latent memory retrieval and elastic budget allocation, improving QA accuracy by 24-26% and ALFWorld success by 27-66% over baselines with lower token cost.
AGORA is an inference-free step-level compressor for LLM agent prompts that retains at least 75% of uncompressed performance in most tested settings where token-level methods collapse due to action-grammar destruction.
Life-Harness evolves reusable interventions from training trajectories to enhance frozen LLM agents on unseen tasks across seven deterministic environments, yielding 88.5% average relative improvement in 116 of 126 model-environment settings.
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
SkillOps maintains LLM skill libraries via Skill Contracts and ecosystem graphs, raising ALFWorld task success to 79.5% as a standalone agent and improving retrieval baselines by up to 2.9 points with near-zero library-time LLM cost.
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
MemCompiler reframes memory use as state-conditioned compilation, delivering relevant guidance via text and latent channels to improve embodied agent performance up to 129% and cut latency 60% versus static injection.
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
TCOD stabilizes on-policy distillation for multi-turn agents via temporal curriculum on trajectory depth, improving performance up to 18 points over vanilla OPD and sometimes surpassing the teacher.
citing papers explorer
-
When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
LongAct benchmark evaluates long-horizon household task execution from free-form instructions; HoloMind agent raises performance but top VLMs still reach only 59% goal completion and 16% full-task success.
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
-
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
UCOB uses local return comparisons between skill and no-skill views to choose which view teaches the other, improving agent training on ALFWorld and WebShop.
-
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents
Replay pairing shows LLM agents do not persist plans in hidden states but rely on plans remaining in context, with rapid signal decay and task performance drops when plans are evicted.
-
SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models
SMAC-Talk is a new benchmark that adds natural language messaging and deceptive-agent scenarios to SMAC for testing LLM coordination in multi-agent environments.
-
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
AGORA is an inference-free step-level compressor for LLM agent prompts that retains at least 75% of uncompressed performance in most tested settings where token-level methods collapse due to action-grammar destruction.
-
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
Life-Harness evolves reusable interventions from training trajectories to enhance frozen LLM agents on unseen tasks across seven deterministic environments, yielding 88.5% average relative improvement in 116 of 126 model-environment settings.
-
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
-
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
Belief Memory: Agent Memory Under Partial Observability
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
-
Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents
A small parametric transition model plus a Jaccard consistency gate grounds LLM agent state deltas, cutting hallucinated-state rate ~80% and raising success from 0.668 to 0.838 on graph planning benchmarks.
-
Where Do CoT Training Gains Land in LLM based Agents?
CoT training in LLM agents improves prompt-action quality more than the advantage of generated reasoning, and selectively masking action supervision improves out-of-domain generalization.
-
Diagnosing Task Insensitivity in Language Agents
The paper diagnoses task insensitivity in LLM agents as a cause of weak OOD generalization, links it to attention drift, and proposes Task-Perturbed NLL Optimization as a contrastive regularizer to improve task dependence.
-
Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention
Action-conditioned estimation of intervention advantage via prefix branching reduces control regret over calibrated scalar risk scores in LLM agent oversight across benchmarks.
-
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
HarnessX composes typed harness components, evolves them from execution traces via a four-stage meta-agent pipeline, and jointly fine-tunes the agent model, reporting +14.5% average peak gains on five benchmarks (validated only on the evolution set).
-
From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents
In LLM agents, reward-hack activation marks a latent policy state, but next-step risky behavior is best predicted when that signal is combined with token entropy and decision context.
-
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
SkillPyramid introduces a hierarchical skill consolidation framework with self-evolution, reporting 38% higher average reward and 27.7% fewer execution steps on ALFWorld, WebShop, and ScienceWorld across four models.
-
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
SkillRevise iteratively refines initial LLM-generated agent skills using execution traces to diagnose defects and apply repairs, raising success rates from 36.05% to 61.63% on SkillsBench across three benchmarks and five LLMs.
-
Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions
POLAR organizes prior interactions into a multimodal knowledge graph with semantic and episodic memory to improve personalized embodied task execution across multiple MLLM backbones.
-
Test-Time Deep Thinking to Explore Implicit Rules
TTExplore trains a 7B thinker via task-score RL to infer implicit rules at test time, raising agent success by 14-19 points on five embodied tasks.
-
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.
-
Verifiable Process Rewards for Agentic Reasoning
VPR converts symbolic, constraint, or posterior oracles into dense turn-level rewards for RL, improving credit assignment in agentic reasoning and transferring to general benchmarks.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
From History to State: Constant-Context Skill Learning for LLM Agents
Constant-context skill learning trains reusable task-family modules for LLM agents using a deterministic state block for progress tracking and subgoal rewards, achieving 89.6% unseen success on ALFWorld, 76.8% on WebShop, and 66.4% on SciWorld with Qwen3-8B while reducing prompt tokens 2-7x.
-
T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
T²PO improves stability and performance in multi-turn agentic RL by using uncertainty dynamics at token and turn levels to guide exploration and avoid wasted rollouts.
-
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning
EgoTSR applies a three-stage curriculum on a 46-million-sample dataset to build egocentric spatiotemporal reasoning, reaching 92.4% accuracy on long-horizon tasks and reducing chronological biases.
-
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
-
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
WebFactory is a fully automated RL pipeline that compresses LLM-encoded internet knowledge into grounded web agents, achieving performance comparable to human-annotated training but using synthetic data from only 10 websites.
-
HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents
HiMAC decomposes LLM agent tasks into macro planning and micro execution using critic-free hierarchical RL and iterative co-evolution, outperforming baselines on ALFWorld, WebShop, and Sokoban.
-
AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
AgentXRay formulates workflow reconstruction as combinatorial optimization and uses Monte Carlo Tree Search with Red-Black Pruning to approximate black-box agent behaviors via output-based proxy metrics.
-
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
ECHO jointly optimizes policy and critic via co-evolution, cascaded rollouts, and saturation-aware shaping to deliver non-stale feedback and higher success in open-world LLM agent RL.
-
Differentiable Evolutionary Reinforcement Learning
DERL is a differentiable bi-level method that evolves optimal reward structures for RL policies by composing atomic primitives and using meta-gradients from validation performance.
-
Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning
BPO framework achieves state-of-the-art performance with improved token efficiency on ALFWorld, ScienceWorld, and WebShop by bootstrapping efficient reasoning, extrapolating via curriculum, and refining on reward-selected experiences.
-
Cognitive Architectures for Language Agents
CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic development of capable agents.
-
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance.
-
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
SkillReranker decomposes tasks and skills into state transitions, builds an execution graph, and adaptively selects skills per task stage, improving agent performance on ALFWorld and ScienceWorld.
-
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
-
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
An agentic harness letting the LLM self-manage flat text-file storage via tool calls outperforms eight prior memory systems on cross-scenario generality across QA, chat, trajectory, stress-test, and long-horizon tasks.
-
DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
DeltaMem uses two residual trees to store goal-conditioned skills and scene knowledge as incremental deltas from shared roots, with failure-penalized retrieval and autonomous consolidation, outperforming baselines in interactive environments.
-
Echo: Learning from Experience Data via User-Driven Refinement
Echo is a framework that harvests user-driven refinements of agent proposals as training signals to align models with real-world needs, demonstrated by raising code completion acceptance from 25.7% to 35.7% in production.
-
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
TaskGround introduces a Ground-Infer-Execute framework for full-scene household reasoning that improves success rates on the FullHome benchmark and enables compact models to match larger ones at up to 18x lower token cost.
-
Interactive Evaluation Requires a Design Science
Interactive evaluation of AI must be reframed as a distinct paradigm that maps interaction trajectories to judgments on process, recoverability, coordination, robustness, and system performance, supported by a two-axis taxonomy and design principles.
-
From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
-
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
ReCAPA adds predictive correction and multi-level semantic alignment to VLA models, plus two new metrics for tracking error spread and recovery, yielding competitive benchmark results over LLM baselines.
-
Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism
A staged LLM pipeline synthesizes verifiable discrete-event world models from natural language specifications using the DEVS formalism for long-horizon consistency in LLM agents.
-
End-to-end PDDL Planning with Hardcoded and Dynamic Agents
An end-to-end LLM framework refines natural language into valid PDDL domains and problems via hardcoded and dynamic agents, generates plans with standard engines, and returns readable output.
-
Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective
The paper analyzes CPU bottlenecks in agentic AI serving, selects representative workloads, and demonstrates that CPU-aware scheduling optimizations COMB and MAS can reduce P50 latency by up to 1.7x and total latency by up to 2.49x on two hardware systems.