Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
hub
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
46 Pith papers cite this work. Polarity classification is still indexing.
46
Pith papers citing it
abstract
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving. ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices. Our experiments show that ToT significantly enhances language models' problem-solving abilities on three novel tasks requiring non-trivial planning or search: Game of 24, Creative Writing, and Mini Crosswords. For instance, in Game of 24, while GPT-4 with chain-of-thought prompting only solved 4% of tasks, our method achieved a success rate of 74%. Code repo with all prompts: https://github.com/princeton-nlp/tree-of-thought-llm.
hub tools
citation-role summary
background 1
citation-polarity summary
claims ledger
- abstract Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoug
co-cited works
roles
background 1polarities
background 1representative citing papers
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
SkCC compiles LLM skills via SkIR to achieve portability across agent frameworks, reduce adaptation effort from O(m×n) to O(m+n), and enforce security with reported gains in task success rates and token efficiency.
AuDisAgent reformulates multimodal controversy detection as a dynamic audience dissemination process using screening, panel discussion, and arbitration agents, plus comment bootstrapping, and reports outperforming prior static methods on a public dataset.
Entropy-guided supertokens from BPE on reasoning traces compress LLM outputs by 8.1% on average across models and math benchmarks with no accuracy loss while exposing strategy differences between correct and incorrect traces.
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
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.
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
AgentFlow uses a typed graph DSL covering roles, prompts, tools, topology and protocol plus a runtime-signal feedback loop to optimize multi-agent harnesses, reaching 84.3% on TerminalBench-2 and discovering ten new zero-days in Chrome including two critical sandbox escapes.
The conceptual multiverse system with a verification framework for decision structures helps users in philosophy, AI alignment, and poetry build clearer working maps of open-ended problems by making implicit LLM choices explicit and changeable.
SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.
FORGE uses a reasoning-action-observation loop and Dynamic Forest of Agents to perform scalable LLM-based binary analysis, finding 1,274 vulnerabilities across 591 of 3,457 real-world firmware binaries at 72.3% precision and broader coverage than prior methods.
BEAM reformulates LLM-based heuristic design as bi-level optimization using GA for structures, MCTS for placeholders, and adaptive memory to outperform prior single-layer methods on CVRP and MIS tasks.
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
IoT-Brain uses a neuro-symbolic Spatial Trajectory Graph to ground LLMs for verifiable semantic-spatial sensor scheduling, achieving 37.6% higher task success with lower resource use on a campus-scale benchmark.
ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.
Set-of-Mark prompting marks segmented image regions with alphanumerics and masks to let GPT-4V achieve state-of-the-art zero-shot results on referring expression comprehension and segmentation benchmarks like RefCOCOg.
Chain-of-Thought reasoning in LLMs is often unfaithful, with models relying on it variably by task and less so as models scale larger.
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.
RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.
LLM-X is a scalable architecture for direct negotiation and communication among personal LLM agents, featuring federated gateways, typed protocols, and policy enforcement, shown stable in experiments with up to 12 agents.
A practical evaluation protocol for AI pentesting agents that uses validated vulnerability discovery, LLM semantic matching, and bipartite scoring to assess performance in realistic, complex targets.
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.
citing papers explorer
-
Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning
Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
-
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
SkCC compiles LLM skills via SkIR to achieve portability across agent frameworks, reduce adaptation effort from O(m×n) to O(m+n), and enforce security with reported gains in task success rates and token efficiency.
-
From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework
AuDisAgent reformulates multimodal controversy detection as a dynamic audience dissemination process using screening, panel discussion, and arbitration agents, plus comment bootstrapping, and reports outperforming prior static methods on a public dataset.
-
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Entropy-guided supertokens from BPE on reasoning traces compress LLM outputs by 8.1% on average across models and math benchmarks with no accuracy loss while exposing strategy differences between correct and incorrect traces.
-
TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
-
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.
-
RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
-
Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
AgentFlow uses a typed graph DSL covering roles, prompts, tools, topology and protocol plus a runtime-signal feedback loop to optimize multi-agent harnesses, reaching 84.3% on TerminalBench-2 and discovering ten new zero-days in Chrome including two critical sandbox escapes.
-
Navigating the Conceptual Multiverse
The conceptual multiverse system with a verification framework for decision structures helps users in philosophy, AI alignment, and poetry build clearer working maps of open-ended problems by making implicit LLM choices explicit and changeable.
-
SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.
-
Feedback-Driven Execution for LLM-Based Binary Analysis
FORGE uses a reasoning-action-observation loop and Dynamic Forest of Agents to perform scalable LLM-based binary analysis, finding 1,274 vulnerabilities across 591 of 3,457 real-world firmware binaries at 72.3% precision and broader coverage than prior methods.
-
BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design
BEAM reformulates LLM-based heuristic design as bi-level optimization using GA for structures, MCTS for placeholders, and adaptive memory to outperform prior single-layer methods on CVRP and MIS tasks.
-
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
-
IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
IoT-Brain uses a neuro-symbolic Spatial Trajectory Graph to ground LLMs for verifiable semantic-spatial sensor scheduling, achieving 37.6% higher task success with lower resource use on a campus-scale benchmark.
-
Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism
ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.
-
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Set-of-Mark prompting marks segmented image regions with alphanumerics and masks to let GPT-4V achieve state-of-the-art zero-shot results on referring expression comprehension and segmentation benchmarks like RefCOCOg.
-
Measuring Faithfulness in Chain-of-Thought Reasoning
Chain-of-Thought reasoning in LLMs is often unfaithful, with models relying on it variably by task and less so as models scale larger.
-
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
-
LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.
-
RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning
RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.
-
LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents
LLM-X is a scalable architecture for direct negotiation and communication among personal LLM agents, featuring federated gateways, typed protocols, and policy enforcement, shown stable in experiments with up to 12 agents.
-
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
A practical evaluation protocol for AI pentesting agents that uses validated vulnerability discovery, LLM semantic matching, and bipartite scoring to assess performance in realistic, complex targets.
-
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.
-
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
PopQuiz Attack infers LLM training data membership by turning examples into quiz questions and measuring answer accuracy, reaching 0.873 average ROC-AUC across six models and outperforming prior methods by 20.6%.
-
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
-
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
Distilling and retrieving reusable reasoning skills lets LLMs solve coding and math problems with fewer tokens and higher accuracy.
-
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Verbal Process Supervision uses structured critiques from stronger models in an iterative loop to improve LLM reasoning, reaching 94.9% on GPQA Diamond and large gains on AIME 2025.
-
Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code
Dual Reasoning with explicit safety audits improves the new SUDS metric by 1.32x to 3.42x over baselines on code generation benchmarks containing injected harmful keywords.
-
DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation
DCD introduces a domain-oriented hierarchical decomposition and staged routing workflow that restricts retrieval and generation scopes progressively to improve robustness and factual accuracy in RAG on complex, multi-source queries.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Repeated sampling scales problem coverage log-linearly with sample count, improving SWE-bench Lite performance from 15.9% to 56% using 250 samples.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
-
Complexity Horizons of Compressed Models in Analog Circuit Analysis
Prerequisite graphs map compressed LLM performance boundaries in analog circuit analysis to allow selecting the smallest viable model for a given task complexity.
-
State Representation and Termination for Recursive Reasoning Systems
Recursive reasoning systems can represent their state via an epistemic state graph and terminate when the linearized order-gap is non-degenerate near the fixed point, providing a local condition for when the stopping rule is informative.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
-
A pragmatic approach to regulating AI agents
AI agents require distinct regulation as AI systems under the EU AI Act with orchestration-layer oversight and a risk-based traffic light authorization system in contract law to preserve human accountability.
-
Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis
Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.
-
From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection
Enforcing structured reflection via Outlines-based constrained decoding on an 8B LLM triggers structure snowballing instead of better self-correction, producing near-perfect syntax but persistent semantic errors and revealing an alignment tax.
-
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Llama Guard is an instruction-tuned Llama2-7b model that performs multi-class safety classification on prompts and responses, matching or exceeding existing moderation tools on benchmarks while supporting taxonomy customization.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.
-
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Dual-Track CoT lets small language models perform reliable multi-step reasoning with the same or fewer tokens via budget tracking and rejection of redundant steps.
-
Understanding the planning of LLM agents: A survey
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
-
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a taxonomy and summary table.