AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Paper • 2606.05622 • Published • 32 •
3
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 3 hours ago
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints commentedon a paper about 3 hours ago
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution commentedon a paper about 3 hours ago
TIDE: Proactive Multi-Problem Discovery via Template-Guided IterationOrganizations
None yet
commented 4
papers about 3 hours ago
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Paper • 2606.06492 • Published • 44 •
2
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
Paper • 2606.04743 • Published • 36 •
3
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
Paper • 2606.05553 • Published • 40 •
3
commented 4
papers 1 day ago
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Paper • 2606.02060 • Published • 49 •
7
Trust Region On-Policy Distillation
Paper • 2606.01249 • Published • 41 •
2
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
Paper • 2605.23895 • Published • 51 •
2
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
Paper • 2606.00683 • Published • 83 •
6
commented 8
papers 2 days ago
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Paper • 2605.28556 • Published • 63 •
3
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
Paper • 2605.29707 • Published • 139 •
3
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Paper • 2606.02437 • Published • 174 •
4
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Paper • 2605.30611 • Published • 189 •
3
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
Paper • 2605.30993 • Published • 56 •
3
Trust-Region Behavior Blending for On-Policy Distillation
Paper • 2605.31159 • Published • 64 •
4
GrepSeek: Training Search Agents for Direct Corpus Interaction
Paper • 2605.29307 • Published • 102 •
5
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Paper • 2605.31264 • Published • 105 •
3
commented 4
papers 9 days ago
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
Paper • 2605.26114 • Published • 64 •
3
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
Paper • 2605.27367 • Published • 71 •
4
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
Paper • 2605.23271 • Published • 79 •
3
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 138 •
4