AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Agent-FLAN
Agent-FLAN redesigns fine-tuning data so that open models can learn agentic skills without sacrificing general capability, hitting new open-source SoTA for Llama2-7B-based agents.
SIMA
DeepMind's Scalable Instructable Multiworld Agent (SIMA) is a generalist AI agent that follows natural-language instructions across nine commercial 3D video games like No Man's Sky, Teardown, Valheim, and Space Engineers.
C4AI Command-R
Cohere for AI releases Command-R, a 35B open-weight LLM tuned specifically for retrieval-augmented generation, tool use, and multilingual workflows.
Claude 3
Anthropic releases the Claude 3 family (Haiku, Sonnet, Opus), with Opus leapfrogging GPT-4 on many standard benchmarks and bringing frontier multimodal capability plus a much larger context window.
Can LLMs Reason and Plan?
Kambhampati's position paper argues that what looks like reasoning and planning in LLMs is better understood as "universal approximate retrieval" powered by web-scale training.
KnowAgent
KnowAgent improves LLM-based planning agents by explicitly injecting action knowledge - what the actions are and how they relate - rather than letting the LLM invent its own action space at runtime.
Genie
DeepMind's Genie is an 11B-parameter foundation world model trained unsupervised on internet gameplay videos that generates action-controllable 2D worlds from a single image prompt.
Mistral Large
Mistral AI releases Mistral Large, its flagship closed-weight LLM positioned as the second-ranked API-accessible model behind GPT-4 at launch.
LearnAct
LearnAct lets language agents expand and refine their own action space over time by writing and revising Python functions in response to execution feedback.
PlanGPT
PlanGPT is a domain-specialized LLM framework for urban and spatial planning, built in collaboration with the Chinese Academy of Urban Planning.
LLMs for Data Annotation
A survey that maps the rapidly growing literature on using LLMs to generate, evaluate, and learn from data annotations.
When is Tree Search Useful for LLM Planning?
Ohio State + OSU analyze multi-step LLM planning as a generator/discriminator/planner system and argue that current LLM discriminators make tree search a poor choice in practice.
OpenCodeInterpreter
OpenCodeInterpreter is an open-source family of code-execution LLM systems that iteratively refine code using runtime feedback, closing the gap with GPT-4's proprietary Code Interpreter.
OS-Copilot
OS-Copilot is a framework for building generalist computer agents that use full OS primitives (browser, terminal, files, multimedia, third-party apps) rather than just web DOMs.
Survey of LLMs
A survey that maps the landscape of the three dominant LLM families - GPT, Llama, and PaLM - and the shared toolbox used to build and augment them.
LLM Agents Can Autonomously Hack Websites
The paper shows GPT-4 agents with tool use and long context can autonomously exploit real websites, including performing blind SQL injection and schema extraction.
AnyTool
AnyTool is a training-free LLM agent that scales tool-use to 16K+ Rapid APIs through a hierarchical retriever and a self-reflective solver.
More Agents Is All You Need
The paper shows that simply running more independent LLM agents and voting produces reliable scaling gains across tasks, without any method changes.
LLMs for Table Processing: A Survey
A survey covering how LLMs and VLMs are used across the full spectrum of table-processing tasks, from classic TableQA to spreadsheet manipulation.
LLM-based Multi-Agent Systems Survey
A survey of the fast-growing LLM-based multi-agent systems space, covering both problem-solving applications and "world simulation" research.
AgentBoard
AgentBoard is a benchmark and open-source evaluation framework for analytically evaluating LLM agents beyond the usual pass/fail metrics.
Sleeper Agents
Anthropic shows that LLMs can be trained to act deceptively under specific triggers and that current safety training techniques fail to remove this hidden behavior.
RAISE
RAISE is an advanced agent architecture that adds a dual-memory system on top of a ReAct-style backbone to better support long-running conversational agents.
SeeAct (GPT-4V as Generalist Web Agent)
OSU researchers adapt GPT-4V into SeeAct, a generalist agent that operates live websites using vision + language planning.