ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
hub
Webshop: Towards scalable real-world web interaction with grounded language agents
24 Pith papers cite this work. Polarity classification is still indexing.
24
Pith papers citing it
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
MultiUAV-Plat supplies a new RESTful simulation platform and 1500-task benchmark where Agent4Drone reaches 57.9% task pass rate versus 30.6% for ReAct baseline across 75 multi-UAV missions.
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.
JobBench is a new benchmark with 130 occupational tasks where the best of 36 tested AI models achieves only 45.9% success.
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
Introduces Trajectory Proper Score (TPS) as a strictly proper family of trajectory-level scoring rules that elicits the complete prefix-conditioned success probability process.
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.
UI traces of actions and timings from LLM browser agents enable identification of the underlying model with up to 96% F1 across 14 models and multiple tasks.
RecoAtlas is a benchmark that evaluates LLM recommendation agents on behavior-grounded metrics for relevance, complementarity, and diversity in addition to semantic coherence.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
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.
PhoneBuddy combines real-app and mock-app RL after shared SFT, raising real-phone task success from 36.67% to 45.33% and AndroidWorld from 60.3% to 83.2%.
HANSEL extracts navigable evidence from agent trajectories with 83.7% precision and 88.8% recall on 45 tasks, reduces volume by 61.6%, and improves verification metrics in a 14-participant study.
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.
Introduces SII framework and PIWM using AIDA and BDI models to predict intent transitions and select from five intervention classes, reporting 0.641 macro F1 with ground-truth state on a new benchmark.
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
ActFocus resolves the action bottleneck in agentic RL by reweighting token gradients toward action tokens using observed reward variance and an energy-based uncertainty term, outperforming PPO and GRPO by up to 65 percentage points.
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.
OpenRath introduces Session as a first-class, branchable runtime value that unifies fragmented state in multi-agent systems and makes fork, merge, and replay explicit operations.
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
TraceGraph constructs shared state graphs from multi-model trajectories to expose productive cores and trap regions, then uses them to diagnose navigation differences across benchmarks and to drive a recovery pipeline that improves SWE-bench resolved rates by 3-4 points on fired instances.
HTMLCure uses browser-executed interaction trajectories to diagnose and repair LLM HTML outputs, expanding 97K prompts into a 40K refined SFT set that lifts a 27B model to 50.6 on HTMLBench-400 and 81.2 on MiniAppBench.
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
This overview paper explains the conceptual foundations and design principles of On-Policy Self-Distillation for large language models from a beginner's perspective.
citing papers explorer
-
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
-
MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning
MultiUAV-Plat supplies a new RESTful simulation platform and 1500-task benchmark where Agent4Drone reaches 57.9% task pass rate versus 30.6% for ReAct baseline across 75 multi-UAV missions.
-
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.
-
JobBench: Aligning Agent Work With Human Will
JobBench is a new benchmark with 130 occupational tasks where the best of 36 tested AI models achieves only 45.9% success.
-
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
-
Proper Scoring Rules for Agentic Uncertainty Quantification
Introduces Trajectory Proper Score (TPS) as a strictly proper family of trajectory-level scoring rules that elicits the complete prefix-conditioned success probability process.
-
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.
-
Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
UI traces of actions and timings from LLM browser agents enable identification of the underlying model with up to 96% F1 across 14 models and multiple tasks.
-
RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
RecoAtlas is a benchmark that evaluates LLM recommendation agents on behavior-grounded metrics for relevance, complementarity, and diversity in addition to semantic coherence.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
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.
-
PhoneBuddy: Training Open Models for Agentic Phone Use
PhoneBuddy combines real-app and mock-app RL after shared SFT, raising real-phone task success from 36.67% to 45.33% and AndroidWorld from 60.3% to 83.2%.
-
HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification
HANSEL extracts navigable evidence from agent trajectories with 83.7% precision and 88.8% recall on 45 tasks, reduces volume by 61.6%, and improves verification metrics in a 14-participant study.
-
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.
-
See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence
Introduces SII framework and PIWM using AIDA and BDI models to predict intent transitions and select from five intervention classes, reporting 0.641 macro F1 with ground-truth state on a new benchmark.
-
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
-
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
ActFocus resolves the action bottleneck in agentic RL by reweighting token gradients toward action tokens using observed reward variance and an energy-based uncertainty term, outperforming PPO and GRPO by up to 65 percentage points.
-
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.
-
OpenRath: Session-Centered Runtime State for Agent Systems
OpenRath introduces Session as a first-class, branchable runtime value that unifies fragmented state in multi-agent systems and makes fork, merge, and replay explicit operations.
-
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
-
TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
TraceGraph constructs shared state graphs from multi-model trajectories to expose productive cores and trap regions, then uses them to diagnose navigation differences across benchmarks and to drive a recovery pipeline that improves SWE-bench resolved rates by 3-4 points on fired instances.
-
HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML
HTMLCure uses browser-executed interaction trajectories to diagnose and repair LLM HTML outputs, expanding 97K prompts into a 40K refined SFT set that lifts a 27B model to 50.6 on HTMLBench-400 and 81.2 on MiniAppBench.
-
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
-
A Brief Overview: On-Policy Self-Distillation In Large Language Models
This overview paper explains the conceptual foundations and design principles of On-Policy Self-Distillation for large language models from a beginner's perspective.