4arXiv cs.CL (Computation and Language)·
PACE framework applies LLMs to algorithmic parent-order execution in trading
Researchers introduce PACE (Plan-Ahead Controlled Execution), a hierarchical LLM-based framework for parent-order execution in algorithmic trading, decomposing the problem into long-horizon planning and short-horizon execution without requiring market assumptions or task-specific training. Evaluated on Shenzhen Stock Exchange Level-1 data, PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines by up to 0.65 basis points. Behavioral analysis finds LLMs exhibit distinct execution patterns from human traders, including earlier execution and a positive correlation between model confidence and performance. This is the first systematic study extending LLM use in finance from asset selection to order execution.
Related guides (1)
Related events (8)
PlanBench-XL: Benchmark for LLM Agent Planning in Large-Scale Tool Ecosystems
Researchers introduce PlanBench-XL, an interactive benchmark of 327 retail tasks spanning 1,665 tools designed to evaluate LLM agents on long-horizon planning under retrieval-limited tool visibility. The benchmark includes a blocking mechanism simulating real-world disruptions such as missing or failing tools, forcing agents to detect and recover from broken execution paths. Experiments on ten leading LLMs reveal severe performance degradation: GPT-5.4 drops from 51.90% accuracy in unblocked settings to 11.36% under the most severe blocking condition, highlighting fragility in adaptive planning for large, imperfect tool environments.
CM-LRS: A capital markets reliability benchmark for LLM workflow outputs
Researchers introduce CM-LRS (Capital Markets LLM Reliability Score), a seven-dimension evaluation framework assessing LLM outputs at the workflow level rather than the question-answer layer, targeting regulated capital-markets use cases such as DCM/ECM term extraction, M&A comparables, and issuer profiling. The benchmark is demonstrated on five workflows using public SEC EDGAR and UK takeover filings, scoring four models across four LLM judges. Key findings: frontier closed-source models cluster tightly (Sonnet 4.6 = 4.31, Opus 4.7 = 4.30, GPT-5.5 = 4.09) while Llama 3.3 70B lags at 3.15, with the gap concentrated in retrieval and synthesis tasks rather than extraction. The work advances domain-specific evaluation methodology for high-stakes financial workflows where regulatory defensibility matters.
LLawCo framework teaches embodied multi-agent LLMs to derive and follow cooperation laws
Researchers from MERL propose LLawCo (Learning Laws of Cooperation), a framework that enables embodied LLM-based agents to autonomously align with partners and task objectives in decentralized, partially observable environments. Agents reflect on past failures to extract misaligned behavioral patterns and derive high-level behavioral laws (e.g., 'Talk when necessary', 'Wait for partner'), which are incorporated into reasoning via supervised fine-tuning. The authors also introduce PARTNR-Dialog, a new large-scale multi-agent communicative planning benchmark, and report average success rate improvements of 4.5% on PARTNR-Dialog and 6.8% on TDW-MAT over state-of-the-art open-source communicative agent frameworks across four backbone LLMs.
TradingAgents: Multi-Agent LLM Financial Trading Framework
TradingAgents is an open-source Python framework by TauricResearch that applies multi-agent LLM architectures to financial trading tasks. The repository has accumulated 81,650 GitHub stars with 284 added today, indicating strong community traction. It represents a concrete deployment pattern for agentic AI systems in quantitative finance.
PROVE framework trains LLMs for multi-step tool use via stateful MCP environments and programmatic rewards
Researchers introduce PROVE (Programmatic Rewards On Verified Environments), a framework for training LLMs to orchestrate multi-step tool calls using reinforcement learning. The system includes a library of 20 stateful MCP servers with 343 tools, an automated data synthesis pipeline that grounds training queries in live server state, and a multi-component programmatic reward function requiring no judge model. Training four models (Qwen3-4B, Qwen3-8B, Qwen2.5-7B, Granite-4.1-8B) with ~13K examples yields gains of up to +10.2 on BFCL Multi-Turn, +6.8 on tau2-bench, and +6.5 on T-Eval, demonstrating consistent improvements in multi-step tool orchestration.
XALPHA: Memory-driven AI agent for end-to-end quantitative trading alpha discovery
Researchers introduce XAlpha, an LLM-based agentic system for continuous hypothesis-to-code alpha factor discovery in quantitative finance. The system uses a multi-source memory architecture with three specialized 'brain' modules (Macro, Micro, Cross) to close the loop from financial hypothesis generation through code implementation, validation, and iterative feedback. Unlike prior LLM-based quant frameworks that automate isolated steps, XAlpha operates as an end-to-end research agent that accumulates and reuses discovery knowledge across cycles. Experiments on the CSI300 index show improved alpha discovery performance over representative baselines.
PPC: Preplan-Plan-CoT Framework for LLM Mathematical Reasoning
This paper introduces PPC (Preplan-Plan-CoT), a reasoning framework that adds an explicit problem-understanding stage (the 'preplan') before the planning and chain-of-thought execution stages in LLM mathematical reasoning. The preplan captures problem type, applicable tools, and foreseeable pitfalls, addressing a gap in existing plan-based methods that only address 'how' to solve without first clarifying 'what' to solve. A three-stage synthesis pipeline with a spoiler-score detector and composite GRPO reward ensures clean preplan supervision and coherent plan generation. Evaluated across four backbones and five math benchmarks, PPC achieves best results on 39 of 40 metrics with +2.23 maj@16 and +3.06 pass@16 improvements over the strongest baseline at no additional inference token cost.
E3 framework reduces LLM agent token costs 91% by estimating task complexity before execution
Researchers introduce E3 (Estimate, Execute, Expand), a framework that addresses over-reading behavior in LLM agents by having them estimate task complexity and execute a minimum viable path before expanding scope. On MSE-Bench, a 121-edit deterministic benchmark, E3 matches 100% task success while cutting cost by 85%, tokens by 91%, and file inspections by 92% versus strong baselines. The authors also validate the approach on a live GPT-4o agent editing a real open-source library, graded against an actual pytest suite. The work formalizes the Agent Cognitive Redundancy Ratio (ACRR) and positions task-aware execution as a step toward engineering-grounded AI.