REVIEW 9 cited by
Symbolic Learning Enables Self-Evolving Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The AI community has been exploring a pathway to artificial general intelligence (AGI) by developing "language agents", which are complex large language models (LLMs) pipelines involving both prompting techniques and tool usage methods. While language agents have demonstrated impressive capabilities for many real-world tasks, a fundamental limitation of current language agents research is that they are model-centric, or engineering-centric. That's to say, the progress on prompts, tools, and pipelines of language agents requires substantial manual engineering efforts from human experts rather than automatically learning from data. We believe the transition from model-centric, or engineering-centric, to data-centric, i.e., the ability of language agents to autonomously learn and evolve in environments, is the key for them to possibly achieve AGI. In this work, we introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers. Specifically, we consider agents as symbolic networks where learnable weights are defined by prompts, tools, and the way they are stacked together. Agent symbolic learning is designed to optimize the symbolic network within language agents by mimicking two fundamental algorithms in connectionist learning: back-propagation and gradient descent. Instead of dealing with numeric weights, agent symbolic learning works with natural language simulacrums of weights, loss, and gradients. We conduct proof-of-concept experiments on both standard benchmarks and complex real-world tasks and show that agent symbolic learning enables language agents to update themselves after being created and deployed in the wild, resulting in "self-evolving agents".
Forward citations
Cited by 9 Pith papers
-
FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification
FVRuleLearner retrieves learned operator-level reasoning rules to boost the functional correctness of LLM-generated SystemVerilog assertions by roughly 30 percentage points over simple prompting baselines.
-
Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
A clarification-first 3D agent, trained by simulated multi-turn dialogue, reaches 60.4% and 43.3% success on single- and multi-step 3D tool tasks, more than doubling prior baselines.
-
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
A single LLM is trained with multi-agent distilled trajectories plus agentic RL, and the resulting Chain-of-Agents models set state-of-the-art Pass@1 scores among tool-integrated reasoning methods on GAIA, BrowseComp,...
-
TaskCraft: Automated Generation of Agentic Tasks
TaskCraft automatically generates verifiable, multi-tool agentic tasks with execution trajectories via atomic task construction and depth/width extension, and fine-tuning on the resulting 36,000-task dataset improves ...
-
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
G-Memory stores past multi-agent teamwork in a three-tier graph and retrieves it to boost performance on five benchmarks.
-
Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning
Cognify uses a budget-adaptive hierarchical search to automatically tune gen-AI workflows, reporting up to 2.8x quality gains, 10x cost cuts, and 2.7x latency cuts on six benchmarks.
-
OAgents: An Empirical Study of Building Effective Agents
OAgents reports a framework and ablation study claiming open-source state-of-the-art on GAIA, but the empirical evidence is weakened by benchmark fitting and missing statistics.
-
Scaling Test-time Compute for LLM Agents
On the GAIA benchmark, Best-of-N sampling with list-wise answer selection gives the largest agent gains, and selective (score-triggered) reflection beats reflection at every step.
-
WebDancer: Towards Autonomous Information Seeking Agency
A four-stage data-and-training pipeline (synthetic QA, trajectory rejection sampling, SFT, DAPO reinforcement learning) produces WebDancer, a web agent that outperforms vanilla ReAct and several open-source agentic fr...
Discussion (0). Continue with ORCID to comment.